Mark W. Schmidt

发表

SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient

Aaron Mishkin, Frederik Kunstner, Didrik Nielsen, 2018, NeurIPS.

Structure learning in random fields for heart motion abnormality detection

Mark W. Schmidt, Kevin P. Murphy, Glenn Fung, 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

Convex Optimization for Big Data: Scalable, randomized, and parallel algorithms for big data analytics pdf

Volkan Cevher, Mark W. Schmidt, Stephen Becker, 2014, IEEE Signal Processing Magazine.

Where are the Masks: Instance Segmentation with Image-level Supervision pdf

Mark W. Schmidt, David Vázquez, Issam H. Laradji, 2019, BMVC.

Convex Structure Learning in Log-Linear Models: Beyond Pairwise Potentials

Mark W. Schmidt, Kevin P. Murphy, Kevin P. Murphy, 2010, AISTATS.

An interior-point stochastic approximation method and an L1-regularized delta rule

Mark W. Schmidt, Nando de Freitas, Peter Carbonetto, 2008, NIPS.

Hierarchical Maximum-Margin Clustering pdf

Mark W. Schmidt, Greg Mori, Leonid Sigal, 2015, ArXiv.

Learning Graphical Model Structure Using L1-Regularization Paths

Mark W. Schmidt, Kevin P. Murphy, Alexandru Niculescu-Mizil, 2007, AAAI.

Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition

Mark W. Schmidt, Hamed Karimi, Julie Nutini, 2016, ECML/PKDD.

Convergence of Proximal-Gradient Stochastic Variational Inference under Non-Decreasing Step-Size Sequence pdf

Mark W. Schmidt, Mohammad Emtiyaz Khan, Masashi Sugiyama, 2015, ArXiv.

Fast and Simple Natural-Gradient Variational Inference with Mixture of Exponential-family Approximations

Mark W. Schmidt, Mohammad Emtiyaz Khan, Wu Lin, 2019, ICML.

Fast Optimization Methods for L1 Regularization: A Comparative Study and Two New Approaches

Mark W. Schmidt, Glenn Fung, Rómer Rosales, 2007, ECML.

Learning a Classification-based Glioma Growth Model Using MRI Data

Mark W. Schmidt, Russell Greiner, Jörg Sander, 2006, J. Comput..

A Classification-Based Glioma Diffusion Model Using MRI Data

Mark W. Schmidt, Russell Greiner, Jörg Sander, 2006, Canadian Conference on AI.

Where are the Blobs: Counting by Localization with Point Supervision pdf

Mark W. Schmidt, David Vázquez, Issam H. Laradji, 2018, ECCV.

Modeling Discrete Interventional Data using Directed Cyclic Graphical Models pdf

Mark W. Schmidt, Kevin P. Murphy, K. Murphy, 2009, UAI.

Erratum to: Minimizing finite sums with the stochastic average gradient

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

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.

Causal learning without DAGs

Mark W. Schmidt, Kevin P. Murphy, David Duvenaud, 2008, NIPS Causality: Objectives and Assessment.

A simpler approach to obtaining an O(1/t) convergence rate for the projected stochastic subgradient method pdf

Mark W. Schmidt, Francis R. Bach, Simon Lacoste-Julien, 2012, ArXiv.

Support Vector Random Fields for Spatial Classification

Mark W. Schmidt, Chi-Hoon Lee, Russell Greiner, 2005, PKDD.

Minimizing finite sums with the stochastic average gradient

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

Increased discrimination in level set methods with embedded conditional random fields

Mark W. Schmidt, Dana Cobzas, D. Cobzas, 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

Modeling annotator expertise: Learning when everybody knows a bit of something

Mark W. Schmidt, Gerardo Hermosillo, Jennifer G. Dy, 2010, AISTATS.

Non-Uniform Stochastic Average Gradient Method for Training Conditional Random Fields pdf

Mark W. Schmidt, Anoop Sarkar, Mohamed Osama Ahmed, 2015, AISTATS.

3D Variational Brain Tumor Segmentation using a High Dimensional Feature Set

Mark W. Schmidt, Martin Jägersand, Dana Cobzas, 2007, 2007 IEEE 11th International Conference on Computer Vision.

Convex Optimization for Big Data: Scalable, randomized, and parallel algorithms for big data analytics

Volkan Cevher, Mark W. Schmidt, Stephen Becker, 2014, IEEE Signal Processing Magazine.

Instance Segmentation with Point Supervision pdf

Mark W. Schmidt, David Vázquez, Issam H. Laradji, 2019, ArXiv.

Erratum: Hybrid Deterministic-Stochastic Methods for Data Fitting

Mark W. Schmidt, Michael P. Friedlander, 2013, SIAM J. Sci. Comput..

A Stochastic Gradient Method with an Exponential Convergence Rate for Finite Training Sets

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

Hybrid Deterministic-Stochastic Methods for Data Fitting

Mark W. Schmidt, Michael P. Friedlander, M. Friedlander, 2011, SIAM J. Sci. Comput..

Convergence Rates of Inexact Proximal-Gradient Methods for Convex Optimization

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

Convergence Rates for Greedy Kaczmarz Algorithms, and Randomized Kaczmarz Rules Using the Orthogonality Graph

Mark W. Schmidt, Issam H. Laradji, Julie Nutini, 2016, UAI.

“Active-set complexity” of proximal gradient: How long does it take to find the sparsity pattern?

Mark W. Schmidt, Warren Hare, Julie Nutini, 2017, Optim. Lett..

Fast and Faster Convergence of SGD for Over-Parameterized Models and an Accelerated Perceptron pdf

Mark W. Schmidt, Francis Bach, Sharan Vaswani, 2018, AISTATS.

Generalized Fast Approximate Energy Minimization via Graph Cuts: a-Expansion b-Shrink Moves

Mark W. Schmidt, Karteek Alahari, Alahari Karteek, 2011, UAI.

StopWasting My Gradients: Practical SVRG

Mark W. Schmidt, Mohamed Osama Ahmed, Scott Sallinen, 2015, NIPS.

Accelerated training of conditional random fields with stochastic gradient methods

Mark W. Schmidt, S. V. N. Vishwanathan, Kevin P. Murphy, 2006, ICML.

Faster Stochastic Variational Inference using Proximal-Gradient Methods with General Divergence Functions

Mark W. Schmidt, Mohammad Emtiyaz Khan, Masashi Sugiyama, 2015, UAI.

Segmenting Brain Tumors with Conditional Random Fields and Support Vector Machines

Mark W. Schmidt, Chi-Hoon Lee, Russell Greiner, 2005, CVBIA.

Optimizing Costly Functions with Simple Constraints: A Limited-Memory Projected Quasi-Newton Algorithm

Mark W. Schmidt, Kevin P. Murphy, Michael P. Friedlander, 2009, AISTATS.

Group Sparse Priors for Covariance Estimation

Mark W. Schmidt, Kevin P. Murphy, Benjamin M. Marlin, 2009, UAI.

Generalized Fast Approximate Energy Minimization via Graph Cuts: Alpha-Expansion Beta-Shrink Moves pdf

Mark W. Schmidt, Karteek Alahari, Alahari Karteek, 2011, ArXiv.

Convergence Rates for Greedy Kaczmarz Algorithms, and Randomized Kaczmarz Rules Using the Orthogonality Graph pdf

Mark W. Schmidt, Issam H. Laradji, Julie Nutini, 2016, UAI.

On Sparse, Spectral and Other Parameterizations of Binary Probabilistic Models

Mark W. Schmidt, Nando de Freitas, David Poole, 2012, AISTATS.

Coordinate Descent Converges Faster with the Gauss-Southwell Rule Than Random Selection pdf

Mark W. Schmidt, Michael P. Friedlander, Issam H. Laradji, 2015, ICML.

Block-Coordinate Frank-Wolfe Optimization for Structural SVMs

Mark W. Schmidt, Martin Jaggi, Simon Lacoste-Julien, 2012, ICML.

Segmenting brain tumors using alignment-based features

Mark W. Schmidt, Russell Greiner, Ilya Levner, 2005, Fourth International Conference on Machine Learning and Applications (ICMLA'05).

Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates

Aaron Mishkin, Mark W. Schmidt, Issam H. Laradji, 2019, NeurIPS.

GROUP SPARSITY VIA LINEAR-TIME PROJECTION

Mark W. Schmidt, K. Murphy, E. Berg, 2008 .

Fast Convergence of Stochastic Gradient Descent under a Strong Growth Condition

Mark W. Schmidt, Nicolas Le Roux, 2013, 1308.6370.

Optimization Methods for ` 1-Regularization

Mark W. Schmidt, 2009 .

Ju n 20 18 Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Lojasiewicz Condition

Mark W. Schmidt, H. Karimi, J. Nutini, 2018 .

Linear Convergence of Proximal-Gradient Methods under the Polyak-Łojasiewicz Condition

Mark W. Schmidt, H. Karimi, 2015 .

A Hybrid Stochastic-deterministic Optimization Method for Waveform Inversion

Mark W. Schmidt, M. Friedlander, T. Leeuwen, 2011 .

Convergence rate of stochastic gradient with constant step size

Mark W. Schmidt, 2014 .

Let's Make Block Coordinate Descent Go Fast: Faster Greedy Rules, Message-Passing, Active-Set Complexity, and Superlinear Convergence

Mark W. Schmidt, Issam H. Laradji, J. Nutini, 2017 .

Let's Make Block Coordinate Descent Go Fast: Faster Greedy Rules, Message-Passing, Active-Set Complexity, and Superlinear Convergence

Mark W. Schmidt, Issam H. Laradji, J. Nutini, 2017, 1712.08859.

Play and Learn: Using Video Games to Train Computer Vision Models pdf

James J. Little, Mark W. Schmidt, Alireza Shafaei, 2016, BMVC.

Graphical model structure learning using L₁-regularization

Mark W. Schmidt, Mark Schmidt, 2010 .

11 Projected Newton-type Methods in Machine Learning

Mark W. Schmidt, 2011 .

Online Learning Rate Adaptation with Hypergradient Descent pdf

Mark W. Schmidt, Frank D. Wood, Mark Schmidt, 2017, ICLR.

Convergence Rates for Greedy Kaczmarz Algorithms

Mark W. Schmidt, Julie Nutini Ubc, Behrooz Sepehry Ubc, 2015 .

Adaptive Gradient Methods Converge Faster with Over-Parameterization (and you can do a line-search) pdf

Frederik Kunstner, Mark W. Schmidt, Issam H. Laradji, 2020, ArXiv.

Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates

Mark W. Schmidt, Issam H. Laradji, S. Lacoste-Julien, 2019, NeurIPS.

Least Squares Optimization with L 1-Norm Regularization

Mark W. Schmidt, Mark Schmidt, 2005 .

Manifold identification of gradient-related proximal methods : Appendix

Mark W. Schmidt, J. Nutini, Yifan Sun, 2019 .

Let's Make Block Coordinate Descent Converge Faster: Faster Greedy Rules, Message-Passing, Active-Set Complexity, and Superlinear Convergence

Mark W. Schmidt, Issam H. Laradji, J. Nutini, 2017, 1712.08859.

Let's Make Block Coordinate Descent Converge Faster: Faster Greedy Rules, Message-Passing, Active-Set Complexity, and Superlinear Convergence

Mark W. Schmidt, Issam H. Laradji, J. Nutini, 2017, 1712.08859.

Homeomorphic-Invariance of EM: Non-Asymptotic Convergence KL Divergence for Exponential Families via Mirror Descent (Extended Abstract)

Mark W. Schmidt, Raunak Kumar, Frederik Kunstner, 2022 .

Inferring Parameters for an Elementary Step Model of DNA Structure Kinetics with Locally Context-Dependent Arrhenius Rates

Mark W. Schmidt, Mark Schmidt, Erik Winfree, 2017, DNA.

The pathway elaboration method for mean first passage time estimation in large continuous-time Markov chains with applications to nucleic acid kinetics

Mark W. Schmidt, Erik Winfree, Anne Condon, 2021, 2101.03657.

Homeomorphic-Invariance of EM: Non-Asymptotic Convergence in KL Divergence for Exponential Families via Mirror Descent

Mark W. Schmidt, Raunak Kumar, Frederik Kunstner, 2020, AISTATS.

Stein's Lemma for the Reparameterization Trick with Exponential Family Mixtures pdf

Mark W. Schmidt, Mohammad Emtiyaz Khan, Wu Lin, 2019, ArXiv.

Variance-Reduced Methods for Machine Learning

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

Does Your Model Know the Digit 6 Is Not a Cat? A Less Biased Evaluation of "Outlier" Detectors pdf

James J. Little, Mark W. Schmidt, Alireza Shafaei, 2018, ArXiv.

Combining Bayesian optimization and Lipschitz optimization

Mark W. Schmidt, Mark Schmidt, Mohamed Osama Ahmed, 2018, Machine Learning.

Tractable structured natural gradient descent using local parameterizations

Mark W. Schmidt, M. E. Khan, F. Nielsen, 2021, ICML.

Robust Asymmetric Learning in POMDPs

Mark W. Schmidt, Frank D. Wood, A. Scibior, 2020, ICML.

Noise Is Not the Main Factor Behind the Gap Between SGD and Adam on Transformers, but Sign Descent Might Be

Mark W. Schmidt, Frederik Kunstner, Jacques Chen, 2023, ICLR.

Distributed Maximization of "Submodular plus Diversity" Functions for Multi-label Feature Selection on Huge Datasets

Mark W. Schmidt, Mark Schmidt, Mehrdad Ghadiri, 2019, AISTATS.

Do we need “ Harmless ” Bayesian Optimization and “ First-Order ” Bayesian Optimization ?

Mark W. Schmidt, Mohamed Osama Ahmed, Bobak Shahriari, 2016 .

A Less Biased Evaluation of Out-of-distribution Sample Detectors

James J. Little, Mark W. Schmidt, Alireza Shafaei, 2018, BMVC.

Fast Patch-based Style Transfer of Arbitrary Style pdf

Mark W. Schmidt, Mark Schmidt, Tian Qi Chen, 2016, ArXiv.

Fast Convergence of Random Reshuffling under Over-Parameterization and the Polyak-Łojasiewicz Condition

Mark W. Schmidt, Christos Thrampoulidis, Chen Fan, 2023, arXiv.org.

Proposal-Based Instance Segmentation With Point Supervision

Mark W. Schmidt, Issam H. Laradji, Pedro H. O. Pinheiro, 2020, 2020 IEEE International Conference on Image Processing (ICIP).

SVRG meets AdaGrad: painless variance reduction pdf

Mark W. Schmidt, Reza Babanezhad, Sharan Vaswani, 2021, Machine Learning.

Target-based Surrogates for Stochastic Optimization

Mark W. Schmidt, Nicolas Le Roux, Sharan Vaswani, 2023, ICML.

Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation

Mark W. Schmidt, S. Lacoste-Julien, Sharan Vaswani, 2019, AISTATS.

Improved Policy Optimization for Online Imitation Learning

Mark W. Schmidt, Sharan Vaswani, J. W. Lavington, 2022, CoLLAs.

New Insights into Bootstrapping for Bandits pdf

Zheng Wen, Mark W. Schmidt, Mark Schmidt, 2018, ArXiv.

Efficient Deep Gaussian Process Models for Variable-Sized Inputs

Vladimir Pavlovic, Mark W. Schmidt, Mark Schmidt, 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

Searching for Optimal Per-Coordinate Step-sizes with Multidimensional Backtracking

Mark W. Schmidt, Victor S. Portella, Frederik Kunstner, 2023, ArXiv.

Don't be so Monotone: Relaxing Stochastic Line Search in Over-Parameterized Models

Mark W. Schmidt, H. Rauhut, Leonardo Galli, 2023, ArXiv.

Are we there yet? Manifold identification of gradient-related proximal methods

Mark W. Schmidt, Yifan Sun, Julie Nutini, 2019, AISTATS.

BiSLS/SPS: Auto-tune Step Sizes for Stable Bi-level Optimization

Mark W. Schmidt, Christos Thrampoulidis, Chen Fan, 2023, arXiv.org.

Analyzing and Improving Greedy 2-Coordinate Updates for Equality-Constrained Optimization via Steepest Descent in the 1-Norm

Mark W. Schmidt, Jennifer She, Aaron Mishkin, 2023, ArXiv.

Regret Bounds without Lipschitz Continuity: Online Learning with Relative-Lipschitz Losses pdf

Mark W. Schmidt, Nicholas J. A. Harvey, Victor S. Portella, 2020, NeurIPS.

Model-Independent Online Learning for Influence Maximization

Laks V. S. Lakshmanan, Zheng Wen, Mark W. Schmidt, 2017, ICML.

Handling the Positive-Definite Constraint in the Bayesian Learning Rule

Mark W. Schmidt, M. E. Khan, Wu Lin, 2020, ICML.

Projected Newton-type methods in machine learning

Mark W. Schmidt, Suvrit Sra, Mark Schmidt, 2011 .

Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning

Mark W. Schmidt, M. E. Khan, M. Leok, 2023, International Conference on Machine Learning.

Structured second-order methods via natural gradient descent pdf

Frank Nielsen, Mark W. Schmidt, Wu Lin, 2021, ArXiv.

LassoOrderSearch: Learning Directed Graphical Model Structure using L1-Penalized Regression and Order Search

Mark W. Schmidt, Mark Schmidt, 2006 .

Efficient Parameter Estimation for DNA Kinetics Modeled as Continuous-Time Markov Chains

Mark W. Schmidt, Erik Winfree, Anne Condon, 2019, DNA.

MASAGA: A Linearly-Convergent Stochastic First-Order Method for Optimization on Manifolds

Mark W. Schmidt, Alireza Shafaei, Mark Schmidt, 2018, ECML/PKDD.

MASAGA: A Stochastic Algorithm for Manifold Optimization

Mark W. Schmidt, Alireza Shafaei, Reza Babanezhad, 2018 .