F. Bach

Michael I. Jordan, Francis R. Bach, F. Bach, 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

Learning mid-level features for recognition

Jean Ponce, Y-Lan Boureau, Yann LeCun, 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

Supervised Dictionary Learning

Guillermo Sapiro, Jean Ponce, Andrew Zisserman, 2008, NIPS.

Discriminative learned dictionaries for local image analysis

Guillermo Sapiro, Jean Ponce, Andrew Zisserman, 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

A Stochastic Gradient Method with an Exponential Convergence Rate for Strongly-Convex Optimization with Finite Training Sets pdf

Mark W. Schmidt, Nicolas Le Roux, Francis R. Bach, 2012, ArXiv.

Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n)

Eric Moulines, Francis R. Bach, F. Bach, 2013, NIPS.

Learning Graphical Models with Mercer Kernels

Michael I. Jordan, Francis R. Bach, F. Bach, 2002, NIPS.

Stochastic Variance Reduction Methods for Saddle-Point Problems

Francis R. Bach, Balamurugan Palaniappan, F. Bach, 2016, NIPS.

Clusterpath: an Algorithm for Clustering using Convex Fusion Penalties

Francis R. Bach, Jean-Philippe Vert, Armand Joulin, 2011, ICML.

Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed pdf

Nicolas Usunier, Francis Bach, Léon Bottou, 2019, ArXiv.

Unsupervised Image Matching and Object Discovery as Optimization

Patrick Pérez, Jean Ponce, Kai Han, 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Multiple kernel learning, conic duality, and the SMO algorithm

Michael I. Jordan, Gert R. G. Lanckriet, Francis R. Bach, 2004, ICML.

Low-rank matrix factorization with attributes pdf

Francis R. Bach, Theodoros Evgeniou, Jean-Philippe Vert, 2006, ArXiv.

Discriminative Sparse Image Models for Class-Specific Edge Detection and Image Interpretation

Martial Hebert, Jean Ponce, Julien Mairal, 2008, ECCV.

Stochastic Optimization for Large-scale Optimal Transport

Gabriel Peyré, Francis R. Bach, Marco Cuturi, 2016, NIPS.

Fast Kernel Learning using Sequential Minimal Optimization

Michael I. Jordan, Gert R. G. Lanckriet, F. Bach, 2004 .

Self-concordant analysis for logistic regression pdf

Francis R. Bach, F. Bach, 2009, ArXiv.

Convergence Rates of Inexact Proximal-Gradient Methods for Convex Optimization

Mark W. Schmidt, Nicolas Le Roux, Francis R. Bach, 2011, NIPS.

Optimization with Sparsity-Inducing Penalties pdf

Julien Mairal, Francis R. Bach, Guillaume Obozinski, 2011, Found. Trends Mach. Learn..

Low-Rank Optimization on the Cone of Positive Semidefinite Matrices

Francis R. Bach, Pierre-Antoine Absil, Rodolphe Sepulchre, 2008, SIAM J. Optim..

Multiscale Mining of fMRI Data with Hierarchical Structured Sparsity

Bertrand Thirion, Francis R. Bach, Guillaume Obozinski, 2012, SIAM J. Imaging Sci..

Local stability and robustness of sparse dictionary learning in the presence of noise pdf

Rémi Gribonval, Francis R. Bach, Rodolphe Jenatton, 2012, ArXiv.

Convex Sparse Matrix Factorizations pdf

Jean Ponce, Julien Mairal, Francis R. Bach, 2008, ArXiv.

Averaged Least-Mean-Squares: Bias-Variance Trade-offs and Optimal Sampling Distributions

Francis R. Bach, Alexandre Défossez, F. Bach, 2015, AISTATS.

Discriminative clustering for image co-segmentation

Jean Ponce, Francis R. Bach, Armand Joulin, 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

Low-rank optimization for semidefinite convex problems

F. Bach, P. Absil, R. Sepulchre, 2008, 0807.4423.

Consistency of Kernel Canonical Correlation Analysis

Kenji Fukumizu, Arthur Gretton, Francis Bach, 2005 .

From Averaging to Acceleration, There is Only a Step-size

Francis R. Bach, Nicolas Flammarion, F. Bach, 2015, COLT.

Global alignment of protein–protein interaction networks by graph matching methods

Francis Bach, Jean-Philippe Vert, Mikhail Zaslavskiy, 2009, Bioinform..

A Continuized View on Nesterov Acceleration for Stochastic Gradient Descent and Randomized Gossip pdf

Hadrien Hendrikx, Francis Bach, Nicolas Flammarion, 2021, ArXiv.

Low-Rank Optimization with Trace Norm Penalty

Bamdev Mishra, Francis R. Bach, Rodolphe Sepulchre, 2011, SIAM J. Optim..

Convex Relaxation for Combinatorial Penalties pdf

Francis R. Bach, Guillaume Obozinski, G. Obozinski, 2012, ArXiv.

Convex optimization with sparsity-inducing norms

Julien Mairal, Guillaume Obozinski, Francis Bach, 2011 .

Task-Driven Dictionary Learning

Jean Ponce, Julien Mairal, Francis R. Bach, 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

Learning with Submodular Functions: A Convex Optimization Perspective

Francis R. Bach, F. Bach, 2011, Found. Trends Mach. Learn..

Convex relaxations of structured matrix factorizations pdf

Francis R. Bach, F. Bach, 2013, ArXiv.

Clustered Multi-Task Learning: A Convex Formulation

Jean-Philippe Vert, Francis Bach, Laurent Jacob, 2008, NIPS.

On the Equivalence between Herding and Conditional Gradient Algorithms pdf

Francis R. Bach, Guillaume Obozinski, Simon Lacoste-Julien, 2012, ICML.

Sharp analysis of low-rank kernel matrix approximations

Francis R. Bach, F. Bach, Francis R. Bach, 2012, COLT.

Non-local sparse models for image restoration

Guillermo Sapiro, Jean Ponce, Andrew Zisserman, 2009, 2009 IEEE 12th International Conference on Computer Vision.

Consistency of the group Lasso and multiple kernel learning pdf

Francis R. Bach, F. Bach, 2007, J. Mach. Learn. Res..

Proximal Methods for Sparse Hierarchical Dictionary Learning

Julien Mairal, Francis R. Bach, Guillaume Obozinski, 2010, ICML.

Automatic annotation of human actions in video

Jean Ponce, Ivan Laptev, Francis R. Bach, 2009, 2009 IEEE 12th International Conference on Computer Vision.

Considering Cost Asymmetry in Learning Classifiers

Eric Horvitz, Francis R. Bach, David Heckerman, 2006, J. Mach. Learn. Res..

Image Classification with Segmentation Graph Kernels

Zaïd Harchaoui, Francis R. Bach, F. Bach, 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

Partially Encrypted Machine Learning using Functional Encryption pdf

David Pointcheval, Francis Bach, Romain Gay, 2019, NeurIPS 2019.

More efficiency in multiple kernel learning

Yves Grandvalet, Stéphane Canu, Francis R. Bach, 2007, ICML '07.

Asymptotically Optimal Regularization in Smooth Parametric Models

Michael I. Jordan, Guillaume Bouchard, Francis R. Bach, 2009, NIPS.

Duality Between Subgradient and Conditional Gradient Methods pdf

Francis R. Bach, F. Bach, 2012, SIAM J. Optim..

Statistical Convergence of Kernel CCA

Kenji Fukumizu, Arthur Gretton, Francis R. Bach, 2005, NIPS.

Network Flow Algorithms for Structured Sparsity

Julien Mairal, Francis R. Bach, Guillaume Obozinski, 2010, NIPS.

DIFFRAC: a discriminative and flexible framework for clustering

Zaïd Harchaoui, Francis R. Bach, F. Bach, 2007, NIPS.

Tree-dependent Component Analysis

Michael I. Jordan, Francis R. Bach, F. Bach, 2002, UAI.

Sparse and Spurious: Dictionary Learning With Noise and Outliers

Rémi Gribonval, Francis R. Bach, Rodolphe Jenatton, 2014, IEEE Transactions on Information Theory.

Full regularization path for sparse principal component analysis

Alexandre d'Aspremont, Laurent El Ghaoui, Francis R. Bach, 2007, ICML '07.

On Lazy Training in Differentiable Programming

Francis Bach, Edouard Oyallon, Lenaic Chizat, 2018, NeurIPS.

Averaging Stochastic Gradient Descent on Riemannian Manifolds

Michael I. Jordan, Nilesh Tripuraneni, Francis Bach, 2018, COLT.

FINDING CLUSTERS IN INDEPENDENT COMPONENT ANALYSIS

Michael I. Jordan, F. Bach, 2003 .

Testing for Homogeneity with Kernel Fisher Discriminant Analysis

Zaïd Harchaoui, Eric Moulines, Francis R. Bach, 2007, NIPS.

PAC-Bayesian Theory Meets Bayesian Inference

Alexandre Lacoste, Francis R. Bach, Pascal Germain, 2016, NIPS.

On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport

Francis Bach, Lenaïc Chizat, F. Bach, 2018, NeurIPS.

Weakly Supervised Action Labeling in Videos under Ordering Constraints pdf

Cordelia Schmid, Jean Ponce, Ivan Laptev, 2014, ECCV.

Sparse Modeling for Image and Vision Processing pdf

Jean Ponce, Julien Mairal, Francis R. Bach, 2014, Found. Trends Comput. Graph. Vis..

Predictive low-rank decomposition for kernel methods

Michael I. Jordan, Francis R. Bach, F. Bach, 2005, ICML.

Spectral Norm Regularization of Orthonormal Representations for Graph Transduction

Francis R. Bach, Chiranjib Bhattacharyya, Raman Sankaran, 2015, NIPS.

Lov asz # function, SVMs and nding dense subgraphs

Devdatt P. Dubhashi, F. Bach, C. Bhattacharyya, 2013 .

Massively scalable Sinkhorn distances via the Nyström method pdf

Alessandro Rudi, Francis Bach, Jason Altschuler, 2018, NeurIPS.

A unified perspective on convex structured sparsity: Hierarchical, symmetric, submodular norms and beyond

G. Obozinski, F. Bach, 2016 .

Integration Methods and Accelerated Optimization Algorithms

F. Bach, A. d'Aspremont, Vincent Roulet, 2017, 1702.06751.

Optimal Solutions for Sparse Principal Component Analysis pdf

Alexandre d'Aspremont, Laurent El Ghaoui, Francis R. Bach, 2007, J. Mach. Learn. Res..

Many-to-Many Graph Matching: a Continuous Relaxation Approach pdf

Francis R. Bach, Jean-Philippe Vert, Mikhail Zaslavskiy, 2010, ECML/PKDD.

Learning graphical models for stationary time series

Michael I. Jordan, Francis R. Bach, F. Bach, 2004, IEEE Transactions on Signal Processing.

On the Equivalence between Quadrature Rules and Random Features pdf

Francis R. Bach, F. Bach, 2015, ArXiv.

Structured sparsity through convex optimization pdf

Julien Mairal, Francis R. Bach, Guillaume Obozinski, 2011, ArXiv.

Weakly-Supervised Alignment of Video with Text

Cordelia Schmid, Jean Ponce, Ivan Laptev, 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

On the Path to an Ideal ROC Curve: Considering Cost Asymmetry in Learning Classifiers

Eric Horvitz, Francis R. Bach, David Heckerman, 2005, AISTATS.

Metric Learning for Temporal Sequence Alignment

Damien Garreau, Francis R. Bach, Sylvain Arlot, 2014, NIPS.

Primal-dual algorithms for non-negative matrix factorization with the Kullback-Leibler divergence

Francis R. Bach, Felipe Yanez, F. Bach, 2014, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Discriminative training of hidden Markov models for multiple pitch tracking [speech processing examples]

Michael I. Jordan, Francis R. Bach, F. Bach, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss pdf

Francis Bach, Lenaic Chizat, F. Bach, 2020, COLT.

Slice inverse regression with score functions

Francis Bach, F. Bach, Dmitry Babichev, 2018 .

Learning theory from first principles Lecture 8: Neural networks

F. Bach, 2020 .

Dimensionality Reduction for Supervised Learning with Reproducing Kernel Hilbert Spaces

Michael I. Jordan, F. Bach, K. Fukumizu, 2004 .

Theoretical Understanding of Batch-normalization: A Markov Chain Perspective pdf

Francis Bach, Thomas Hofmann, Jonas Kohler, 2020, ArXiv.

Optimization for Machine Learning

F. Bach, 2010 .

Learning theory from first principles Lecture 1: Introduction to supervised learning

F. Bach, 2020 .

Learning theory from first principles Lecture 9: Special topics

F. Bach, 2020 .

Optimal Convergence Rates for Convex Distributed Optimization in Networks

Kilian Q. Weinberger, Francis Bach, Kevin Scaman, 2019, J. Mach. Learn. Res..

Learning theory from first principles Lecture 6: Kernel methods

F. Bach, 2020 .

Journal of Machine Learning Research X (2008) 1-34 Submitted 01/08; Revised 08/08; Published XX/XX

F. Bach, Yves Grandvalet, S. Canu, 2008 .

Active-set Methods for Submodular Optimization

F. Bach, K. S. S. Kumar, 2015 .

Beyond Least-Squares: Fast Rates for Regularized Empirical Risk Minimization through Self-Concordance

Alessandro Rudi, Francis Bach, Ulysse Marteau-Ferey, 2019, COLT.

32nd International Conference on Machine Learning : (ICML 2015) : Lile, France, 6-11 July 2015

David M. Blei, Francis Bach, F. Bach, 2016 .

New Results - Large-Margin Metric Learning for Partitioning Problems

Francis Bach, Sylvain Arlot, Rémi Lajugie, 2013 .

New Results - Active-set Methods for Submodular Optimization

K. S. Sesh Kumar, Francis Bach, F. Bach, 2015 .

IntroductionSpecial issue: Deep learning

Tomaso Poggio, Francis Bach, T. Poggio, 2016 .

Kernel-Based for Testing

Olivier Cappé, Francis Bach, Zaid Harchaoui, 2013 .

New Results - Maximizing submodular functions using probabilistic graphical models

K. S. Sesh Kumar, Francis Bach, F. Bach, 2013 .

New Results - Human activity capture and classification

Cordelia Schmid, Jean Ponce, Visesh Chari, 2011 .

Sparse methods for machine learning Theory and algorithms

Guillaume Obozinski, Francis Bach, G. Obozinski, 2012 .

New Results - Learning and statistical models

Guillaume Bouchard, Julien Mairal, Bin Yu, 2013 .

Machine learning and convex optimization with submodular functions

Francis Bach, F. Bach, 2013 .

Structured sparse methods for matrix factorization

Francis Bach, F. Bach, 2010 .

Machine learning and optimization for massive data

Francis Bach, F. Bach, 2015 .

Models of Visual Object Recognition and Scene Understanding

Jean-Philippe Pons, Jean Ponce, Y-Lan Boureau, 2007 .

Learning with sparsity-inducing norms

Francis Bach, F. Bach, 2008 .

New Results - Image restoration, manipulation and enhancement

Jean Ponce, Andrew Zisserman, Julien Mairal, 2011 .

Large-scale machine learning and convex optimization

Francis Bach, F. Bach, 2015 .

Software and Platforms - SPArse Modeling Software (SPAMS)

Jean Ponce, Julien Mairal, Francis Bach, 2013 .

Tractable performance bounds for compressed sensing.

F. Bach, L. Ghaoui, 2009 .

Learning theory from first principles Lecture 2: Linear least-squares regression

F. Bach, 2020 .

Learning theory from first principles Lecture 4: Optimization for machine learning

F. Bach, 2020 .

Multiple Gaussian Process Models

Cedric Archambeau, Francis Bach, F. Bach, 2011, 1110.5238.

Tree-Walk Kernels for Computer Vision

F. Bach, Z. Harchaoui, Zaïd Harchaoui, 2012 .

NONPARAMETRIC STOCHASTIC APPROXIMATION WITH LARGE STEP-SIZES1 BY AYMERIC DIEULEVEUT

F. Bach, Aymeric Dieuleveut, 2016 .

Learning theory from first principles Lecture 5: Local averaging methods

F. Bach, 2020 .

Erratum to: Minimizing finite sums with the stochastic average gradient

Mark W. Schmidt, Nicolas Le Roux, Francis R. Bach, 2017, Mathematical programming.

1 Convex Optimization with Sparsity-Inducing Norms

F. Bach, 2010 .

Principled Analyses and Design of First-Order Methods with Inexact Proximal Operators pdf

Francis Bach, Mathieu Barr'e, Adrien Taylor, 2020, ArXiv.

Variational inference via Wasserstein gradient flows

F. Bach, P. Rigollet, S. Bonnabel, 2022, ArXiv.

Active Labeling: Streaming Stochastic Gradients

Vivien A. Cabannes, Vianney Perchet, F. Bach, 2022, NeurIPS.

Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays

Blake E. Woodworth, F. Bach, Mathieu Even, 2022, 2206.07638.

Fast Stochastic Composite Minimization and an Accelerated Frank-Wolfe Algorithm under Parallelization

F. Bach, Quentin Berthet, Adrien B. Taylor, 2022, ArXiv.

Sum-of-Squares Relaxations for Information Theory and Variational Inference

F. Bach, 2022, 2206.13285.

A systematic approach to Lyapunov analyses of continuous-time models in convex optimization

F. Bach, Adrien B. Taylor, C'eline Moucer, 2022, SIAM J. Optim..

A Non-asymptotic Analysis of Non-parametric Temporal-Difference Learning

F. Bach, Eloise Berthier, Z. Kobeissi, 2022, NeurIPS.

Polynomial-time Sparse Deconvolution

F. Bach, Hadi Daneshmand, 2022 .

On a Variance-Reduction Correction for Temporal-Difference Learning in the Stochastic Continuous Setting

F. Bach, Z. Kobeissi, 2022 .

On a Variance-Reduction Correction for the Temporal-Difference Learning in the Stochastic Continuous Setting

F. Bach, Z. Kobeissi, 2022, 2202.07960.

Information Theory With Kernel Methods

F. Bach, 2022, IEEE Transactions on Information Theory.

Sum-of-Squares Relaxations for Information Theory and Variational Inference

F. Bach, 2022, ArXiv.

On the Theoretical Properties of Noise Correlation in Stochastic Optimization

F. Bach, Aurélien Lucchi, F. Proske, 2022, NeurIPS.

Fast Stochastic Composite Minimization and an Accelerated Frank-Wolfe Algorithm under Parallelization

F. Bach, Quentin Berthet, Adrien B. Taylor, 2022, NeurIPS.

Variational inference via Wasserstein gradient flows

F. Bach, P. Rigollet, S. Bonnabel, 2022, ArXiv.

A Simple Convergence Proof of Adam and Adagrad

L. Bottou, F. Bach, Nicolas Usunier, 2020, Trans. Mach. Learn. Res..

Submodular functions: from discrete to continuous domains

F. Bach, 2018, Mathematical Programming.

Regularized nonlinear acceleration

F. Bach, Damien Scieur, A. d’Aspremont, 2018, Mathematical Programming.

Regression as Classification: Influence of Task Formulation on Neural Network Features

F. Bach, Jean-Philippe Vert, Quentin Berthet, 2022, ArXiv.

Entropy Maximization with Depth: A Variational Principle for Random Neural Networks

F. Bach, Hadi Daneshmand, Amir Joudaki, 2022, ArXiv.

Learning with Differentiable Pertubed Optimizers

Francis R. Bach, Jean-Philippe Vert, Marco Cuturi, 2020, NeurIPS.

Approximation bounds for sparse principal component analysis

F. Bach, L. Ghaoui, A. d’Aspremont, 2014, Mathematical Programming.

Exponential convergence of sum-of-squares hierarchies for trigonometric polynomials

F. Bach, Alessandro Rudi, 2022, 2211.04889.

Explicit Regularization in Overparametrized Models via Noise Injection

F. Bach, Anant Raj, Hans Kersting, 2022, ArXiv.

The continuous-discrete variational Kalman filter (CD-VKF)

F. Bach, S. Bonnabel, Marc Lambert, 2022, 2022 IEEE 61st Conference on Decision and Control (CDC).

Overcomplete Independent Component Analysis via SDP pdf

Alexandre d'Aspremont, Francis Bach, Alexander S. Wein, 2019, AISTATS.

Sparse Recovery and Dictionary Learning From Nonlinear Compressive Measurements

Mark D. Plumbley, F. Bach, Wenwu Wang, 2018, IEEE Transactions on Signal Processing.

Sample Complexity of Dictionary Learning and Other Matrix Factorizations

Rémi Gribonval, Francis R. Bach, Martin Kleinsteuber, 2013, IEEE Transactions on Information Theory.

On the sample complexity of sparse dictionary learning

Rémi Gribonval, Francis R. Bach, Martin Kleinsteuber, 2014, 2014 IEEE Workshop on Statistical Signal Processing (SSP).

Structured Sparsity and Convex Optimization

Francis R. Bach, F. Bach, 2012, ICPRAM.

Ask the locals: Multi-way local pooling for image recognition

Nicolas Le Roux, Jean Ponce, Y-Lan Boureau, 2011, 2011 International Conference on Computer Vision.

Dictionary Learning for Deblurring and Digital Zoom pdf

Jean Ponce, Julien Mairal, Francis R. Bach, 2011, ArXiv.

Learning hierarchical and topographic dictionaries with structured sparsity

Julien Mairal, Francis R. Bach, Guillaume Obozinski, 2011, Optical Engineering + Applications.

Sparse image representation with epitomes

Jean Ponce, Julien Mairal, Francis Bach, 2011, CVPR 2011.

Proximal Methods for Hierarchical Sparse Coding

Julien Mairal, Francis R. Bach, Guillaume Obozinski, 2010, J. Mach. Learn. Res..

Structured sparsity-inducing norms through submodular functions

Francis R. Bach, F. Bach, 2010, NIPS.

High-Dimensional Non-Linear Variable Selection through Hierarchical Kernel Learning pdf

Francis R. Bach, F. Bach, 2009, ArXiv.

Deep Equals Shallow for ReLU Networks in Kernel Regimes pdf

Francis Bach, Alberto Bietti, F. Bach, 2020, ICLR.

Active learning for misspecified generalized linear models

Francis R. Bach, F. Bach, 2006, NIPS.

ILAB: An Interactive Labelling Strategy for Intrusion Detection

Francis Bach, Anaël Beaugnon, Pierre Chifflier, 2017, RAID.

A note on approximate accelerated forward-backward methods with absolute and relative errors, and possibly strongly convex objectives

Francis Bach, Mathieu Barr'e, Adrien Taylor, 2021, Open J. Math. Optim..

Principled analyses and design of first-order methods with inexact proximal operators

F. Bach, Adrien B. Taylor, Mathieu Barr'e, 2020, Mathematical Programming.

A Continuized View on Nesterov Acceleration pdf

Francis Bach, Nicolas Flammarion, Pierre Gaillard, 2021, ArXiv.

Variance-Reduced Methods for Machine Learning

Mark W. Schmidt, Francis Bach, Robert M. Gower, 2020, Proceedings of the IEEE.

On the Effectiveness of Richardson Extrapolation in Machine Learning pdf

Francis Bach, F. Bach, 2020, ArXiv.

UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization

Volkan Cevher, Francis Bach, Kfir Y. Levy, 2019, NeurIPS.

Stochastic first-order methods: non-asymptotic and computer-aided analyses via potential functions

Francis Bach, Adrien Taylor, F. Bach, 2019, COLT.

Rest-Katyusha: Exploiting the Solution's Structure via Scheduled Restart Schemes

Mike E. Davies, Francis Bach, Mohammad Golbabaee, 2018, NeurIPS.

Structure-Adaptive, Variance-Reduced, and Accelerated Stochastic Optimization

Mike Davies, Francis Bach, Mohammad Golbabaee, 2017, 1712.03156.

Nonlinear Acceleration of Stochastic Algorithms

Alexandre d'Aspremont, Francis R. Bach, Damien Scieur, 2017, NIPS.

Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression pdf

Francis R. Bach, Aymeric Dieuleveut, Nicolas Flammarion, 2016, J. Mach. Learn. Res..

Integration Methods and Optimization Algorithms

Alexandre d'Aspremont, Francis R. Bach, Vincent Roulet, 2017, NIPS.

Regularized nonlinear acceleration

Alexandre d'Aspremont, Francis Bach, Damien Scieur, 2016, Mathematical Programming.

Structured Sparse Principal Component Analysis

Francis R. Bach, Guillaume Obozinski, Rodolphe Jenatton, 2009, AISTATS.

Sparse probabilistic projections

Francis R. Bach, Cédric Archambeau, F. Bach, 2008, NIPS.

Learning with Differentiable Perturbed Optimizers pdf

Francis Bach, Jean-Philippe Vert, Marco Cuturi, 2020, ArXiv.

Learning the Structure for Structured Sparsity

Francis R. Bach, Nino Shervashidze, F. Bach, 2014, IEEE Transactions on Signal Processing.

Hidden Markov tree models for semantic class induction

Francis R. Bach, Edouard Grave, Guillaume Obozinski, 2013, CoNLL.

Structured Penalties for Log-Linear Language Models

Guillaume Bouchard, Julien Mairal, Cédric Archambeau, 2013, EMNLP.

Convex and Network Flow Optimization for Structured Sparsity pdf

Julien Mairal, Francis R. Bach, Guillaume Obozinski, 2011, J. Mach. Learn. Res..

Stochastic algorithms with descent guarantees for ICA

Francis Bach, Alexandre Gramfort, Jean-François Cardoso, 2018, AISTATS.

EM algorithms for ICA pdf

Francis Bach, Alexandre Gramfort, Jean-François Cardoso, 2018, ArXiv.

Beyond CCA: Moment Matching for Multi-View Models pdf

Francis R. Bach, Simon Lacoste-Julien, Anastasia Podosinnikova, 2016, ICML.

Rethinking LDA: Moment Matching for Discrete ICA

Francis R. Bach, Simon Lacoste-Julien, Anastasia Podosinnikova, 2015, NIPS.

Approximating the Quadratic Transportation Metric in Near-Linear Time pdf

Alessandro Rudi, Francis Bach, Jason Altschuler, 2018, ArXiv.

Sample Complexity of Sinkhorn Divergences

Gabriel Peyré, Marco Cuturi, Aude Genevay, 2018, AISTATS.

SegAnnDB: interactive Web-based genomic segmentation

Francis R. Bach, Jean-Philippe Vert, Gudrun Schleiermacher, 2014, Bioinform..

Bolasso: model consistent Lasso estimation through the bootstrap

Francis R. Bach, F. Bach, 2008, ICML '08.

Learning Sparse Penalties for Change-point Detection using Max Margin Interval Regression

Francis R. Bach, Jean-Philippe Vert, Toby Hocking, 2013, ICML.

Kernelized Diffusion maps

F. Bach, Loucas Pillaud-Vivien, 2023, ArXiv.

A convex relaxation for weakly supervised classifiers

Francis R. Bach, Armand Joulin, F. Bach, 2012, ICML.

Music Source Separation in the Waveform Domain pdf

Francis Bach, Nicolas Usunier, Alexandre D'efossez, 2019, ArXiv.

Combinatorial Penalties: Which structures are preserved by convex relaxations?

Volkan Cevher, Francis Bach, Marwa El Halabi, 2017, AISTATS.

Evaluating speech features with the minimal-pair ABX task: analysis of the classical MFC/PLP pipeline

Aren Jansen, Hynek Hermansky, Francis Bach, 2013, INTERSPEECH.

Spectral Clustering for Speech Separation

Michael I. Jordan, F. Bach, 2009 .

Learning Spectral Clustering, With Application To Speech Separation

Michael I. Jordan, Francis R. Bach, F. Bach, 2006, J. Mach. Learn. Res..

Stochastic quasi-gradient methods: variance reduction via Jacobian sketching

F. Bach, Peter Richtárik, R. Gower, 2018, Mathematical Programming.

Optimal Algorithms for Smooth and Strongly Convex Distributed Optimization in Networks

Laurent Massoulié, Yin Tat Lee, Francis R. Bach, 2017, ICML.

Minimizing finite sums with the stochastic average gradient

Mark W. Schmidt, Nicolas Le Roux, Francis R. Bach, 2013, Mathematical Programming.

Signal Processing

Zaïd Harchaoui, Eric Moulines, Francis R. Bach, 2013, 2020 27th International Conference on Mixed Design of Integrated Circuits and System (MIXDES).

Data-driven calibration of linear estimators with minimal penalties

Francis R. Bach, Sylvain Arlot, F. Bach, 2009, NIPS.

Semi-supervised NMF with Time-frequency Annotations for Single-channel Source Separation

Francis R. Bach, Cédric Févotte, Augustin Lefèvre, 2012, ISMIR.

Submodular functions: from discrete to continuous domains

Francis Bach, F. Bach, 2015, Mathematical Programming.

Kernel Square-Loss Exemplar Machines for Image Retrieval

Patrick Pérez, Jean Ponce, Francis R. Bach, 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Online but Accurate Inference for Latent Variable Models with Local Gibbs Sampling

Christophe Dupuy, Francis Bach, F. Bach, 2016, J. Mach. Learn. Res..

Highly-Smooth Zero-th Order Online Optimization

Vianney Perchet, Francis R. Bach, Vianney Perchet, 2016, COLT.

Fast Rates for Structured Prediction

Vivien A. Cabannes, F. Bach, Alessandro Rudi, 2021, COLT.

End-to-End Active Learning for Computer Security Experts

Francis Bach, Anaël Beaugnon, Pierre Chifflier, 2018, AAAI Workshops.

Statistical Consistency of Kernel Canonical Correlation Analysis

Kenji Fukumizu, Arthur Gretton, Francis R. Bach, 2007 .

On the Consistency of Max-Margin Losses

Alex W. Nowak, F. Bach, Alessandro Rudi, 2021, AISTATS.

Max-Margin is Dead, Long Live Max-Margin!

F. Bach, Alessandro Rudi, Alex Nowak-Vila, 2021, ArXiv.

Consistent Structured Prediction with Max-Min Margin Markov Networks

Alessandro Rudi, Francis Bach, Alex Nowak-Vila, 2020, ICML.

On Structured Prediction Theory with Calibrated Convex Surrogate Losses

Francis R. Bach, Anton Osokin, Simon Lacoste-Julien, 2017, NIPS.

Structured and Localized Image Restoration pdf

Jean Ponce, Alessandro Rudi, Francis Bach, 2020, ArXiv.

On the Equivalence between Kernel Quadrature Rules and Random Feature Expansions

Francis R. Bach, F. Bach, 2015, J. Mach. Learn. Res..

Gradient Descent on Infinitely Wide Neural Networks: Global Convergence and Generalization pdf

Francis Bach, Lenaic Chizat, F. Bach, 2021, ArXiv.

Structured Prediction with Partial Labelling through the Infimum Loss

Alessandro Rudi, Francis Bach, Vivien Cabannes, 2020, ICML.

Globally Convergent Newton Methods for Ill-conditioned Generalized Self-concordant Losses

Alessandro Rudi, Francis Bach, Ulysse Marteau-Ferey, 2019, NeurIPS.

Tracking the gradients using the Hessian: A new look at variance reducing stochastic methods

Nicolas Le Roux, Robert M. Gower, Francis R. Bach, 2017, AISTATS.

Multi-task regression using minimal penalties

Francis R. Bach, Sylvain Arlot, Matthieu Solnon, 2011, J. Mach. Learn. Res..

Localized Structured Prediction pdf

Alessandro Rudi, Carlo Ciliberto, Francis Bach, 2018, NeurIPS.

Large-Margin Metric Learning for Partitioning Problems pdf

Francis R. Bach, Sylvain Arlot, Rémi Lajugie, 2013, ArXiv.

A Note on Lazy Training in Supervised Differentiable Programming pdf

Francis Bach, Lénaïc Chizat, F. Bach, 2018, ArXiv.

On the Consistency of Ordinal Regression Methods

Francis R. Bach, Alexandre Gramfort, Fabian Pedregosa, 2014, J. Mach. Learn. Res..

Multiple Operator-valued Kernel Learning

Philippe Preux, Francis R. Bach, Alain Rakotomamonjy, 2012, NIPS.

Sequential Kernel Herding: Frank-Wolfe Optimization for Particle Filtering pdf

Fredrik Lindsten, Francis Bach, Simon Lacoste-Julien, 2015, AISTATS.

Large-Margin Metric Learning for Constrained Partitioning Problems

Francis R. Bach, Sylvain Arlot, Rémi Lajugie, 2014, ICML.

Learning smoothing models of copy number profiles using breakpoint annotations

Francis R. Bach, Jean-Philippe Vert, Gudrun Schleiermacher, 2013, BMC Bioinformatics.

Entropy Maximization with Depth: A Variational Principle for Random Neural Networks

F. Bach, Hadi Daneshmand, Amir Joudaki, 2022, ArXiv.

SING: Symbol-to-Instrument Neural Generator

Nicolas Usunier, Léon Bottou, Neil Zeghidour, 2018, NeurIPS.

Asynchronous Accelerated Proximal Stochastic Gradient for Strongly Convex Distributed Finite Sums pdf

Laurent Massoulié, Hadrien Hendrikx, Francis Bach, 2019, ArXiv.

An Optimal Algorithm for Decentralized Finite Sum Optimization pdf

Hadrien Hendrikx, Francis Bach, Laurent Massoulie, 2020, SIAM J. Optim..

Dual-Free Stochastic Decentralized Optimization with Variance Reduction pdf

Hadrien Hendrikx, Francis Bach, Laurent Massouli'e, 2020, NeurIPS.

An Accelerated Decentralized Stochastic Proximal Algorithm for Finite Sums

Laurent Massoulié, Hadrien Hendrikx, Francis Bach, 2019, NeurIPS.

Accelerated Decentralized Optimization with Local Updates for Smooth and Strongly Convex Objectives

Hadrien Hendrikx, Francis Bach, Laurent Massouli'e, 2018, AISTATS.

Optimal Algorithms for Non-Smooth Distributed Optimization in Networks

Laurent Massoulié, Yin Tat Lee, Sébastien Bubeck, 2018, NeurIPS.

Adaptivity of averaged stochastic gradient descent to local strong convexity for logistic regression pdf

Francis R. Bach, F. Bach, 2013, J. Mach. Learn. Res..

Continuized Accelerations of Deterministic and Stochastic Gradient Descents, and of Gossip Algorithms

F. Bach, Nicolas Flammarion, L. Massoulié, 2021, NeurIPS.

Statistically Preconditioned Accelerated Gradient Method for Distributed Optimization

Lin Xiao, Hadrien Hendrikx, Sebastien Bubeck, 2020, ICML.

Statistical Optimality of Stochastic Gradient Descent on Hard Learning Problems through Multiple Passes

Alessandro Rudi, Francis Bach, Loucas Pillaud-Vivien, 2018, NeurIPS.

Exponential convergence of testing error for stochastic gradient methods pdf

Alessandro Rudi, Francis Bach, Loucas Pillaud-Vivien, 2017, COLT.

Gradient descent for wide two-layer neural networks

Francis Bach, F. Bach, 2020 .

Finite-sample Analysis of M-estimators using Self-concordance

Dmitrii Ostrovskii, Francis Bach, F. Bach, 2018, 1810.06838.

Blind One-microphone Speech Separation: A Spectral Learning Approach

Michael I. Jordan, Francis R. Bach, F. Bach, 2004, NIPS.

F. Bach, Aurélien Lucchi, F. Proske, 2022, ICML.

On the Convergence of Adam and Adagrad pdf

Francis Bach, Nicolas Usunier, Alexandre D'efossez, 2020, ArXiv.

A Tensor-Based Algorithm for High-Order Graph Matching

Jean Ponce, In-So Kweon, Francis R. Bach, 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

Structured Variable Selection with Sparsity-Inducing Norms

Francis R. Bach, Jean-Yves Audibert, Rodolphe Jenatton, 2009, J. Mach. Learn. Res..

A Path Following Algorithm for the Graph Matching Problem

M. Zaslavskiy, F. Bach, J.-P. Vert, 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

Explicit Regularization in Overparametrized Models via Noise Injection

F. Bach, Anant Raj, Hans Kersting, 2022, AISTATS.

Convex Analysis and Optimization with Submodular Functions: a Tutorial pdf

Francis R. Bach, F. Bach, 2010, ArXiv.

Graph kernels between point clouds

Francis R. Bach, F. Bach, 2007, ICML '08.

Convex Optimization over Intersection of Simple Sets: improved Convergence Rate Guarantees via an Exact Penalty Approach

Chiranjib Bhattacharyya, Francis Bach, Achintya Kundu, 2017, AISTATS.

Learning Determinantal Point Processes in Sublinear Time

Francis R. Bach, Christophe Dupuy, F. Bach, 2016, AISTATS.

Screening for a Reweighted Penalized Conditional Gradient Method pdf

Francis Bach, Yifan Sun, F. Bach, 2021, Open J. Math. Optim..

Two Losses Are Better Than One: Faster Optimization Using a Cheaper Proxy

Blake E. Woodworth, F. Bach, Konstantin Mishchenko, 2023, ICML.

Towards closing the gap between the theory and practice of SVRG

Francis Bach, Robert M. Gower, Othmane Sebbouh, 2019, NeurIPS.

Differential Privacy Guarantees for Stochastic Gradient Langevin Dynamics

F. Bach, D. Pointcheval, T. Ryffel, 2022, ArXiv.

Temporal Difference Learning with Continuous Time and State in the Stochastic Setting

F. Bach, Z. Kobeissi, 2022, 2202.07960.

On a Variance Reduction Correction of the Temporal Difference for Policy Evaluation in the Stochastic Continuous Setting

F. Bach, Z. Kobeissi, 2022, ArXiv.

Implicit Regularization of Discrete Gradient Dynamics in Deep Linear Neural Networks

Francis Bach, Gauthier Gidel, Simon Lacoste-Julien, 2019, NeurIPS.

A Path Following Algorithm for Graph Matching

Francis R. Bach, Jean-Philippe Vert, Mikhail Zaslavskiy, 2008, ICISP.

Efficient Algorithms for Non-convex Isotonic Regression through Submodular Optimization

Francis Bach, F. Bach, 2017, NeurIPS.

Finding Actors and Actions in Movies

Cordelia Schmid, Jean Ponce, Ivan Laptev, 2013, 2013 IEEE International Conference on Computer Vision.

Convex Relaxations for Learning Bounded-Treewidth Decomposable Graphs pdf

Francis R. Bach, K. S. Sesh Kumar, F. Bach, 2012, ICML.

Disambiguation of weak supervision with exponential convergence rates pdf

Alessandro Rudi, Francis Bach, Vivien Cabannes, 2021, ArXiv.

Overcoming the curse of dimensionality with Laplacian regularization in semi-supervised learning

Vivien A. Cabannes, F. Bach, Alessandro Rudi, 2020, NeurIPS.

Computing regularization paths for learning multiple kernels

Michael I. Jordan, Francis R. Bach, Romain Thibaux, 2004, NIPS.

Convex Relaxations for Permutation Problems

Alexandre d'Aspremont, Francis R. Bach, Rodolphe Jenatton, 2013, SIAM J. Matrix Anal. Appl..

An online em algorithm in hidden (semi-)Markov models for audio segmentation and clustering

Francis R. Bach, Arshia Cont, Alberto Bietti, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Consistent Dictionary Learning for Signal Declipping

Mark D. Plumbley, Wenwu Wang, Francis Bach, 2018, LVA/ICA.

Iterative hard clustering of features

Alexandre d'Aspremont, Francis Bach, Fajwel Fogel, 2017 .

Learning with Clustering Structure

Alexandre d'Aspremont, Francis Bach, Fajwel Fogel, 2015 .

Learning with Clustering Penalties

Alexandre d'Aspremont, Francis Bach, Vincent Roulet, 2015, 1506.04908.

Supervised Clustering in the Data Cube pdf

Alexandre d'Aspremont, Francis R. Bach, Vincent Roulet, 2015, ArXiv.

Convergence Rates for Non-Log-Concave Sampling and Log-Partition Estimation

F. Bach, David Holzmüller, 2023, ArXiv.

Variational inference via Wasserstein gradient flows

F. Bach, P. Rigollet, S. Bonnabel, 2022, NeurIPS.

Constant Step Size Stochastic Gradient Descent for Probabilistic Modeling pdf

Francis Bach, Dmitry Babichev, F. Bach, 2018, UAI.

Polynomial-time Sparse Measure Recovery: From Mean Field Theory to Algorithm Design

F. Bach, Hadi Daneshmand, 2022, 2204.07879.

Polynomial-time sparse measure recovery

F. Bach, Hadi Daneshmand, 2022, ArXiv.

Learning With Subquadratic Regularization : A Primal-Dual Approach

Francis Bach, Raman Sankaran, Chiranjib Bhattacharyya, 2020, IJCAI.

On the relationship between multivariate splines and infinitely-wide neural networks

F. Bach, 2023, ArXiv.

Sampling from Arbitrary Functions via PSD Models pdf

Alessandro Rudi, Francis R. Bach, Ulysse Marteau-Ferey, 2021, AISTATS.

Multi-class cosegmentation

Jean Ponce, Francis R. Bach, Armand Joulin, 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

Approximation bounds for sparse principal component analysis

Alexandre d'Aspremont, Laurent El Ghaoui, Francis R. Bach, 2012, Math. Program..

Batch normalization provably avoids ranks collapse for randomly initialised deep networks

T. Hofmann, F. Bach, Aurélien Lucchi, 2020, NeurIPS.

Stochastic Composite Least-Squares Regression with Convergence Rate $O(1/n)$

Francis R. Bach, Nicolas Flammarion, F. Bach, 2017, COLT.

Kernel Change-point Analysis

Zaïd Harchaoui, Eric Moulines, Francis R. Bach, 2008, NIPS.

Convergence of Uncertainty Sampling for Active Learning pdf

Francis Bach, Anant Raj, F. Bach, 2021, ICML.

Trace Lasso: a trace norm regularization for correlated designs

Francis R. Bach, Edouard Grave, Guillaume Obozinski, 2011, NIPS.

Multi-scale Mining of fMRI Data with Hierarchical Structured Sparsity

Bertrand Thirion, Francis R. Bach, Guillaume Obozinski, 2011, 2011 International Workshop on Pattern Recognition in NeuroImaging.

Parameter Learning for Log-supermodular Distributions

Francis R. Bach, Tatiana Shpakova, F. Bach, 2016, NIPS.

Reflection methods for user-friendly submodular optimization

Suvrit Sra, Francis Bach, Stefanie Jegelka, 2013, NIPS.

Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays

Blake E. Woodworth, F. Bach, Mathieu Even, 2022, NeurIPS.

Finding Global Minima via Kernel Approximations pdf

Alessandro Rudi, Ulysse Marteau-Ferey, Francis Bach, 2020, Mathematical Programming.

Non-parametric Models for Non-negative Functions pdf

Alessandro Rudi, Francis Bach, Ulysse Marteau-Ferey, 2020, NeurIPS.

Infinite-Dimensional Sums-of-Squares for Optimal Control

Alessandro Rudi, Justin Carpentier, Francis Bach, 2021, 2022 IEEE 61st Conference on Decision and Control (CDC).

Network Flow Algorithms for Structured Sparsity

G. Obozinski, F. Bach, Rodolphe Jenatton, 2010, NIPS.

On Bridging the Gap between Mean Field and Finite Width in Deep Random Neural Networks with Batch Normalization

F. Bach, Hadi Daneshmand, Amir Joudaki, 2022, 2205.13076.

Batch Normalization Orthogonalizes Representations in Deep Random Networks pdf

Francis Bach, Hadi Daneshmand, Amir Joudaki, 2021, NeurIPS.

On the impact of activation and normalization in obtaining isometric embeddings at initialization

F. Bach, Hadi Daneshmand, Amir Joudaki, 2023, ArXiv.

Tight Nonparametric Convergence Rates for Stochastic Gradient Descent under the Noiseless Linear Model pdf

Francis Bach, Pierre Gaillard, Raphael Berthier, 2020, NeurIPS.

High-dimensional analysis of double descent for linear regression with random projections

F. Bach, 2023, ArXiv.

A Universal Algorithm for Variational Inequalities Adaptive to Smoothness and Noise

Francis Bach, Kfir Y. Levy, F. Bach, 2019, COLT.

AriaNN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing

F. Bach, D. Pointcheval, T. Ryffel, 2020, Proc. Priv. Enhancing Technol..

Differentiable Clustering with Perturbed Spanning Forests

F. Bach, Quentin Berthet, F. Llinares-López, 2023, ArXiv.

A tensor-based algorithm for high-order graph matching

Jean Ponce, Olivier Duchenne, Francis Bach, 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

Efficient Primal-Dual Algorithms for Large-Scale Multiclass Classification pdf

Dmitrii Ostrovskii, Francis Bach, Dmitry Babichev, 2019, ArXiv.

Marginal Weighted Maximum Log-likelihood for Efficient Learning of Perturb-and-Map models pdf

Anton Osokin, Francis Bach, Tatiana Shpakova, 2018, UAI.

Model-Consistent Sparse Estimation through the Bootstrap pdf

Francis R. Bach, F. Bach, 2009, ArXiv.

Partially Encrypted Deep Learning using Functional Encryption

Francis Bach, Romain Gay, David Pointcheval, 2019, NeurIPS.

Safe Screening for the Generalized Conditional Gradient Method pdf

Francis Bach, Yifan Sun, F. Bach, 2020, ArXiv.

Signal Processing for Big Data [From the Guest Editors]

Georgios B. Giannakis, Jennifer Neville, Francis R. Bach, 2014, IEEE Signal Process. Mag..

Variational Principles for Mirror Descent and Mirror Langevin Dynamics

F. Bach, M. Raginsky, Anant Raj, 2023, IEEE Control Systems Letters.

1 Convex Optimization with Sparsity-Inducing Norms

F. Bach, 2010 .

Accelerated Gossip in Networks of Given Dimension Using Jacobi Polynomial Iterations

Francis Bach, Pierre Gaillard, Raphael Berthier, 2018, SIAM J. Math. Data Sci..

Online algorithms for nonnegative matrix factorization with the Itakura-Saito divergence

Francis Bach, Cédric Févotte, Augustin Lefèvre, 2011, 2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA).

Regression as Classification: Influence of Task Formulation on Neural Network Features

F. Bach, Jean-Philippe Vert, Quentin Berthet, 2022, International Conference on Artificial Intelligence and Statistics.

Constant Step Size Least-Mean-Square: Bias-Variance Trade-offs and Optimal Sampling Distributions pdf

Francis R. Bach, Alexandre Défossez, F. Bach, 2014, AISTATS 2014.

A General Theory for Structured Prediction with Smooth Convex Surrogates pdf

Alessandro Rudi, Francis Bach, Alex Nowak-Vila, 2019, ArXiv.

The limited-memory recursive variational Gaussian approximation (L-RVGA)

F. Bach, S. Bonnabel, Marc Lambert, 2023, Statistics and Computing.

Stochastic Optimization for Regularized Wasserstein Estimators pdf

Francis Bach, Quentin Berthet, Marin Ballu, 2020, ICML.

Near-optimal estimation of smooth transport maps with kernel sums-of-squares

Alessandro Rudi, Francis Bach, Franccois-Xavier Vialard, 2021, ArXiv.

Convergence Rates for Non-Log-Concave Sampling and Log-Partition Estimation

F. Bach, David Holzmüller, 2023, ArXiv.

Non-Convex Optimization with Certificates and Fast Rates Through Kernel Sums of Squares

Blake E. Woodworth, F. Bach, Alessandro Rudi, 2022, COLT.

Breaking the curse: a dimension free computational upper-bound for smooth optimal transport estimation

F. Bach, François-Xavier Vialard, Alessandro Rudi, 2021 .

Learning With Subquadratic Regularization : A Primal-Dual Approach

F. Bach, C. Bhattacharyya, Raman Sankaran, 2020, IJCAI.

Intersecting singularities for multi-structured estimation

Francis R. Bach, Jean-Philippe Vert, Emile Richard, 2013, ICML.

Gossip of Statistical Observations using Orthogonal Polynomials pdf

Francis Bach, Pierre Gaillard, Raphaël Berthier, 2018, ArXiv.

Maximizing submodular functions using probabilistic graphical models pdf

Francis R. Bach, K. S. Sesh Kumar, F. Bach, 2013, ArXiv.

Fast and Robust Stability Region Estimation for Nonlinear Dynamical Systems

Justin Carpentier, Francis Bach, Eloïse Berthier, 2020, 2021 European Control Conference (ECC).

A unified perspective on convex structured sparsity: Hierarchical, symmetric, submodular norms and beyond

G. Obozinski, F. Bach, 2016 .

Online Regularized Nonlinear Acceleration

Alexandre d'Aspremont, Francis Bach, Edouard Oyallon, 2018 .

Highly-Smooth Zero-th Order Online Optimization Vianney Perchet pdf

Vianney Perchet, Francis R. Bach, Vianney Perchet, 2016, COLT 2016.

Universal Smoothed Score Functions for Generative Modeling

F. Bach, R. Srivastava, Saeed Saremi, 2023, ArXiv.

On the Equivalence between Herding and Conditional Gradient Algorithms

G. Obozinski, F. Bach, S. Lacoste-Julien, 2012, ICML.

Fast Decomposable Submodular Function Minimization using Constrained Total Variation

S. S. Karri, Thomas Pock, Francis Bach, 2019, NeurIPS.

A unified perspective on convex structured sparsity: Hierarchical, symmetric, submodular norms and beyond

G. Obozinski, F. Bach, 2016 .

Active-set Methods for Submodular Minimization Problems

K. S. Sesh Kumar, Francis Bach, F. Bach, 2015, J. Mach. Learn. Res..

Convex Optimization for Parallel Energy Minimization pdf

Suvrit Sra, Francis R. Bach, Stefanie Jegelka, 2015, ArXiv.

Convex Relaxations for Learning Bounded-Treewidth Decomposable Graphs

F. Bach, K. S. S. Kumar, 2012, ICML.

Online but Accurate Inference for Latent Variable Models with Local Gibbs Sampling

F. Bach, Christophe Dupuy, 2016, J. Mach. Learn. Res..

Multiple Operator-valued Kernel Learning

F. Bach, P. Preux, A. Rakotomamonjy, 2012, Neural Information Processing Systems.

Local Component Analysis

Nicolas Le Roux, F. Bach, 2011, ICLR.

Dimensionality Reduction for Supervised Learning with Reproducing Kernel Hilbert Spaces

Michael I. Jordan, F. Bach, K. Fukumizu, 2004, J. Mach. Learn. Res..

Chain of Log-Concave Markov Chains

F. Bach, Saeed Saremi, Ji Won Park, 2023, ArXiv.

A Note on Optimizing Distributions using Kernel Mean Embeddings pdf

Alessandro Rudi, Francis Bach, Boris Muzellec, 2021, ArXiv.

Clusterpath: an Algorithm for Clustering using Convex Fusion Penalties

F. Bach, Jean-Philippe Vert, Armand Joulin, 2011, ICML.

Convex and Network Flow Optimization for Structured Sparsity

G. Obozinski, F. Bach, Rodolphe Jenatton, 2011, J. Mach. Learn. Res..

Task-Driven Dictionary Learning

F. Bach, J. Ponce, J. Mairal, 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

Proximal Methods for Hierarchical Sparse Coding

G. Obozinski, F. Bach, Rodolphe Jenatton, 2010, J. Mach. Learn. Res..

Convex Relaxations for Subset Selection pdf

Alexandre d'Aspremont, Francis R. Bach, Selin Damla Ahipasaoglu, 2010, ArXiv.

Shaping Level Sets with Submodular Functions

Francis Bach, F. Bach, 2010, NIPS.

Combinatorial Penalties: Structure preserved by convex relaxations

Volkan Cevher, Francis Bach, Marwa El Halabi, 2017 .

Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss

F. Bach, Lénaïc Chizat, 2020, COLT.

Deep Equals Shallow for ReLU Networks in Kernel Regimes

F. Bach, A. Bietti, 2020, ICLR.

AriaNN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing

David Pointcheval, Francis Bach, Th'eo Ryffel, 2020, Proc. Priv. Enhancing Technol..

Finding Actors and Actions in Movies

F. Bach, J. Ponce, C. Schmid, 2013, 2013 IEEE International Conference on Computer Vision.

On the impact of activation and normalization in obtaining isometric embeddings at initialization

F. Bach, Hadi Daneshmand, Amir Joudaki, 2023, arXiv.org.

Kernel-Based Methods for Hypothesis Testing: A Unified View

O. Cappé, F. Bach, É. Moulines, 2013, IEEE Signal Process. Mag..

Online dictionary learning for sparse coding

F. Bach, J. Ponce, G. Sapiro, 2009, ICML '09.

Relating Leverage Scores and Density using Regularized Christoffel Functions

Jean-Philippe Vert, Edouard Pauwels, Francis Bach, 2018, NeurIPS.

Full regularization path for sparse principal component analysis

F. Bach, L. Ghaoui, A. d’Aspremont, 2007, International Conference on Machine Learning.

Fast Iterative Shrinkage for Signal Declipping and Dequantization

Mark D. Plumbley, Wenwu Wang, Francis Bach, 2018, 1812.01540.

Nonparametric Linear Feature Learning in Regression Through Regularisation

F. Bach, Umut Simsekli, Bertille Follain, 2023, ArXiv.

Sum-of-Squares Relaxations for Information Theory and Variational Inference

F. Bach, 2022, Foundations of Computational Mathematics.

Theory and applications of the Sum-Of-Squares technique

F. Bach, L. Pesce, Elisabetta Cornacchia, 2023, ArXiv.

Exponential Convergence of Sum-of-Squares Hierarchies for Trigonometric Polynomials

F. Bach, Alessandro Rudi, 2022, SIAM Journal on Optimization.

Information Theory With Kernel Methods

F. Bach, 2022, IEEE Transactions on Information Theory.

Network Flow Algorithms for Structured Sparsity

G. Obozinski, F. Bach, Rodolphe Jenatton, 2010, NIPS.

Second Order Conditions to Decompose Smooth Functions as Sums of Squares

F. Bach, Alessandro Rudi, Ulysse Marteau-Ferey, 2022, SIAM J. Optim..

Sum-of-squares relaxations for polynomial min–max problems over simple sets

F. Bach, 2023, Mathematical Programming.

Explicit Regularization of Stochastic Gradient Methods through Duality pdf

Francis Bach, Anant Raj, F. Bach, 2020, AISTATS.

Tight Nonparametric Convergence Rates for Stochastic Gradient Descent under the Noiseless Linear Model

F. Bach, Raphael Berthier, P. Gaillard, 2020, NeurIPS.

On Bridging the Gap between Mean Field and Finite Width Deep Random Multilayer Perceptron with Batch Normalization

F. Bach, Hadi Daneshmand, Amir Joudaki, 2023, ICML.

Learning smoothing models of copy number profiles using breakpoint annotations

F. Bach, Jean-Philippe Vert, T. Hocking, 2013, BMC Bioinformatics.

On the Sample Complexity of Dictionary Learning

M. Kleinsteuber R. Gribonval R. Jenatton M. Seibert, F. Bach, F. Bach, 2014 .