Florent Krzakala

发表

Asymptotic Characterisation of Robust Empirical Risk Minimisation Performance in the Presence of Outliers

F. Krzakala, Vittorio Erba, Emanuele Troiani, 2023, ArXiv.

Epidemic mitigation by statistical inference from contact tracing data pdf

Florent Krzakala, Luca Dall'Asta, Alfredo Braunstein, 2020, Proceedings of the National Academy of Sciences.

Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures

F. Krzakala, Julien Launay, Iacopo Poli, 2020, NeurIPS.

Simple glass models and their quantum annealing.

F. Krzakala, J. Kurchan, A. Maggs, 2008, Physical Review Letters.

The Quantum Adiabatic Algorithm applied to random optimization problems: the quantum spin glass perspective pdf

Guilhem Semerjian, Florent Krzakala, Victor Bapst, 2012, ArXiv.

Quiet Planting in the Locked Constraint Satisfaction Problems pdf

Florent Krzakala, Lenka Zdeborová, F. Krzakala, 2009, SIAM J. Discret. Math..

Path-integral representation for quantum spin models: Application to the quantum cavity method and Monte Carlo simulations

F. Krzakala, F. Zamponi, G. Semerjian, 2008, 0807.2553.

Gibbs states and the set of solutions of random constraint satisfaction problems

Andrea Montanari, Guilhem Semerjian, Florent Krzakala, 2006, Proceedings of the National Academy of Sciences.

Glassy aspects of melting dynamics (On melting dynamics and the glass transition, Part I)

Lenka Zdeborov'a, Florent Krzakala, 2010, 1006.2480.

Statistical physics of inference: thresholds and algorithms

Florent Krzakala, Lenka Zdeborová, F. Krzakala, 2015, ArXiv.

Phase Transitions in the Coloring of Random Graphs

Florent Krzakala, Lenka Zdeborová, F. Krzakala, 2007, Physical review. E, Statistical, nonlinear, and soft matter physics.

Double Trouble in Double Descent : Bias and Variance(s) in the Lazy Regime

G. Biroli, F. Krzakala, Maria Refinetti, 2020, ICML.

Asymptotic Errors for High-Dimensional Convex Penalized Linear Regression beyond Gaussian Matrices

A. Abbara, Florent Krzakala, Cédric Gerbelot, 2020, Annual Conference Computational Learning Theory.

Asymptotic analysis of the stochastic block model for modular networks and its algorithmic applications

Cristopher Moore, Florent Krzakala, Lenka Zdeborová, 2011, Physical review. E, Statistical, nonlinear, and soft matter physics.

Rigorous dynamical mean field theory for stochastic gradient descent methods

L. Zdeborová, Francesca Mignacco, Emanuele Troiani, 2022, ArXiv.

The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents

Luca Arnaboldi, Emanuele Troiani, Yatin Dandi, 2024, ArXiv.

The Gaussian equivalence of generative models for learning with shallow neural networks

G. Reeves, Lenka Zdeborov'a, Sebastian Goldt, 2020, MSML.

Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification

Florent Krzakala, Pierfrancesco Urbani, Francesca Mignacco, 2020, NeurIPS.

Modeling the Influence of Data Structure on Learning in Neural Networks: The Hidden Manifold Model

F. Krzakala, L. Zdeborová, Sebastian Goldt, 2019, Physical Review X.

Dynamics of stochastic gradient descent for two-layer neural networks in the teacher–student setup pdf

Florent Krzakala, Lenka Zdeborová, Andrew M. Saxe, 2019, NeurIPS.

Escaping mediocrity: how two-layer networks learn hard single-index models with SGD

F. Krzakala, Bruno Loureiro, Luca Arnaboldi, 2023, ArXiv.

Generalization error rates in kernel regression: the crossover from the noiseless to noisy regime

F. Krzakala, Lenka Zdeborov'a, Bruno Loureiro, 2021, NeurIPS.

From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks

F. Krzakala, Bruno Loureiro, Luca Arnaboldi, 2023, COLT.

A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offs

Bruno Loureiro, Matteo Vilucchio, Florent Krzakala, 2024, 2402.05674.

Theoretical characterization of uncertainty in high-dimensional linear classification

F. Krzakala, Lenka Zdeborov'a, Bruno Loureiro, 2022, Machine Learning: Science and Technology.

Learning curves of generic features maps for realistic datasets with a teacher-student model

Florent Krzakala, Bruno Loureiro, Sebastian Goldt, 2021, NeurIPS.

Asymptotic Errors for Teacher-Student Convex Generalized Linear Models (Or: How to Prove Kabashima’s Replica Formula)

F. Krzakala, A. Abbara, C. Gerbelot, 2020, IEEE Transactions on Information Theory.

Capturing the learning curves of generic features maps for realistic data sets with a teacher-student model pdf

Florent Krzakala, Bruno Loureiro, Sebastian Goldt, 2021, ArXiv.

Approximate message-passing for convex optimization with non-separable penalties pdf

Florent Krzakala, Lenka Zdeborová, Gaël Varoquaux, 2018, ArXiv.

The Mutual Information in Random Linear Estimation Beyond i.i.d. Matrices

Nicolas Macris, Florent Krzakala, Jean Barbier, 2018, 2018 IEEE International Symposium on Information Theory (ISIT).

Optimal errors and phase transitions in high-dimensional generalized linear models

Nicolas Macris, Florent Krzakala, Lenka Zdeborová, 2017, Proceedings of the National Academy of Sciences.

The mutual information in random linear estimation

Nicolas Macris, Florent Krzakala, Jean Barbier, 2016, 2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

Mutual information for symmetric rank-one matrix estimation: A proof of the replica formula

Nicolas Macris, Florent Krzakala, Lenka Zdeborová, 2016, NIPS.

Probabilistic reconstruction in compressed sensing: algorithms, phase diagrams, and threshold achieving matrices pdf

Florent Krzakala, Lenka Zdeborová, Yifan Sun, 2012, ArXiv.

Fluctuations, bias, variance and ensemble of learners: exact asymptotics for convex losses in high-dimension

Maria Refinetti, Bruno Loureiro, Florent Krzakala, 2023, Journal of Statistical Mechanics: Theory and Experiment.

Spectral Phase Transitions in Non-Linear Wigner Spiked Models

A. Guionnet, L. Zdeborov'a, Florent Krzakala, 2023, 2310.14055.

Optimal Learning of Deep Random Networks of Extensive-width

F. Krzakala, Hugo Cui, L. Zdeborov'a, 2023, ICML.

On double-descent in uncertainty quantification in overparametrized models

F. Krzakala, L. Zdeborová, Bruno Loureiro, 2022, AISTATS.

Gaussian universality of perceptrons with random labels.

F. Krzakala, Federica Gerace, Bruno Loureiro, 2022, Physical review. E.

Optimal denoising of rotationally invariant rectangular matrices

F. Krzakala, A. Maillard, Vittorio Erba, 2022, MSML.

Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension

F. Krzakala, G. Sicuro, Maria Refinetti, 2022, ICML.

Perturbative construction of mean-field equations in extensive-rank matrix factorization and denoising

F. Krzakala, A. Maillard, Marc M'ezard, 2021, Journal of Statistical Mechanics: Theory and Experiment.

Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed

Florent Krzakala, Sebastian Goldt, Maria Refinetti, 2021, ICML.

The Gaussian equivalence of generative models for learning with two-layer neural networks pdf

Florent Krzakala, Galen Reeves, Lenka Zdeborov'a, 2020, ArXiv.

Generalisation error in learning with random features and the hidden manifold model

Florent Krzakala, Federica Gerace, Bruno Loureiro, 2020, ICML.

On the universality of noiseless linear estimation with respect to the measurement matrix pdf

Florent Krzakala, Lenka Zdeborová, Antoine Baker, 2019, Journal of Physics A: Mathematical and Theoretical.

Entropy and mutual information in models of deep neural networks

Nicolas Macris, Florent Krzakala, Lenka Zdeborová, 2018, NeurIPS.

Gaussian Universality of Linear Classifiers with Random Labels in High-Dimension

Federica Gerace, Bruno Loureiro, Lenka Zdeborov'a, 2022, ArXiv.

A study of uncertainty quantiﬁcation in overparametrized high-dimensional models

F. Krzakala, Bruno Loureiro, Lenka Zdeborov'a, 2022 .

Fundamental limits of Non-Linear Low-Rank Matrix Estimation

L. Zdeborov'a, Florent Krzakala, Justin Ko, 2024, ArXiv.

Estimating rank-one matrices with mismatched prior and noise: universality and large deviations

A. Guionnet, F. Krzakala, Justin Ko, 2023, 2306.09283.

Low-rank Matrix Estimation with Inhomogeneous Noise

A. Guionnet, F. Krzakala, Justin Ko, 2022, 2208.05918.

Spectral Clustering of graphs with the Bethe Hessian

Florent Krzakala, Lenka Zdeborová, Alaa Saade, 2014, NIPS.

Spectral redemption in clustering sparse networks

Elchanan Mossel, L. Zdeborová, Pan Zhang, 2013, Proceedings of the National Academy of Sciences.

Spectral density of the non-backtracking operator on random graphs pdf

Florent Krzakala, Lenka Zdeborová, Alaa Saade, 2014, ArXiv.

Bayesian reconstruction of memories stored in neural networks from their connectivity

F. Krzakala, Lenka Zdeborov'a, N. Brunel, 2021, PLoS Comput. Biol..

Construction of optimal spectral methods in phase retrieval

Yue M. Lu, F. Krzakala, Lenka Zdeborov'a, 2020, MSML.

The Spiked Matrix Model With Generative Priors

Florent Krzakala, Lenka Zdeborová, Bruno Loureiro, 2019, IEEE Transactions on Information Theory.

Marvels and Pitfalls of the Langevin Algorithm in Noisy High-dimensional Inference pdf

Florent Krzakala, Lenka Zdeborová, Giulio Biroli, 2018, Physical Review X.

Phase Transitions, Optimal Errors and Optimality of Message-Passing in Generalized Linear Models pdf

Nicolas Macris, Florent Krzakala, Lenka Zdeborová, 2017, ArXiv.

Constrained low-rank matrix estimation: phase transitions, approximate message passing and applications pdf

Florent Krzakala, Lenka Zdeborová, Thibault Lesieur, 2017, ArXiv.

Spectral bounds for the Ising ferromagnet on an arbitrary given graph

F. Krzakala, Lenka Zdeborov'a, Alaa Saade, 2016, 1609.08269.

Fast Randomized Semi-Supervised Clustering pdf

Florent Krzakala, Marc Lelarge, Lenka Zdeborová, 2016, Journal of Physics: Conference Series.

Clustering from sparse pairwise measurements

Florent Krzakala, Marc Lelarge, Lenka Zdeborová, 2016, 2016 IEEE International Symposium on Information Theory (ISIT).

Spectral detection on sparse hypergraphs

Florent Krzakala, Francesco Caltagirone, Lenka Zdeborová, 2015, 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton).

Matrix Completion from Fewer Entries: Spectral Detectability and Rank Estimation

Florent Krzakala, Lenka Zdeborová, Alaa Saade, 2015, NIPS.

Spectral detection in the censored block model

Florent Krzakala, Marc Lelarge, Alaa Saade, 2015, 2015 IEEE International Symposium on Information Theory (ISIT).

Comparative study for inference of hidden classes in stochastic block models pdf

Florent Krzakala, Lenka Zdeborová, Pan Zhang, 2012, ArXiv.

Phase transition in the detection of modules in sparse networks

F. Krzakala, L. Zdeborová, A. Decelle, 2011, Physical review letters.

Sampling with flows, diffusion and autoregressive neural networks: A spin-glass perspective

F. Krzakala, Yatin Dandi, L. Zdeborov'a, 2023, ArXiv.

Adversarial Robustness by Design Through Analog Computing And Synthetic Gradients

F. Krzakala, Laurent Meunier, Julien Launay, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

The committee machine: computational to statistical gaps in learning a two-layers neural network

Nicolas Macris, Florent Krzakala, Lenka Zdeborová, 2018, NeurIPS.

Learning Gaussian Mixtures with Generalised Linear Models: Precise Asymptotics in High-dimensions

F. Krzakala, L. Zdeborová, G. Sicuro, 2021, NeurIPS.

On melting dynamics and the glass transition. II. Glassy dynamics as a melting process.

F. Krzakala, L. Zdeborová, Florent Krzakala, 2011, The Journal of chemical physics.

On melting dynamics and the glass transition. I. Glassy aspects of melting dynamics.

F. Krzakala, L. Zdeborová, Florent Krzakala, 2011, The Journal of chemical physics.

Decoding from Pooled Data: Sharp Information-Theoretic Bounds

Michael I. Jordan, Florent Krzakala, Lenka Zdeborová, 2016, SIAM J. Math. Data Sci..

Inference in particle tracking experiments by passing messages between images

M Chertkov, M Vergassola, L Kroc, 2009, Proceedings of the National Academy of Sciences.

Phase Transitions and Sample Complexity in Bayes-Optimal Matrix Factorization

Florent Krzakala, Lenka Zdeborová, Ayaka Sakata, 2014, IEEE Transactions on Information Theory.

Statistical and computational phase transitions in spiked tensor estimation

Florent Krzakala, Marc Lelarge, Lenka Zdeborová, 2017, 2017 IEEE International Symposium on Information Theory (ISIT).

TRAMP: Compositional Inference with TRee Approximate Message Passing

F. Krzakala, Lenka Zdeborov'a, Benjamin Aubin, 2020, ArXiv.