Robert M. Gower

79 papers A* 17A 6C 1Journal 55

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Non-Euclidean Gradient Descent Operates at the Edge of Stability. CoRR Rustem Islamov, Michael Crawshaw, Jeremy Cohen, Robert M. Gower
2026	J	`jnl`	Step-Size Stability in Stochastic Optimization: A Theoretical Perspective. CoRR Fabian Schaipp, Robert M. Gower, Adrien B. Taylor
2025	J	`jnl`	An Exploration of Non-Euclidean Gradient Descent: Muon and its Many Variants. CoRR Michael Crawshaw, Chirag Modi, Mingrui Liu, Robert M. Gower
2025	J	`jnl`	Analysis of an Idealized Stochastic Polyak Method and its Application to Black-Box Model Distillation. CoRR Robert M. Gower, Guillaume Garrigos, Nicolas Loizou, Dimitris Oikonomou, Konstantin Mishchenko, Fabian Schaipp
2025	J	`jnl`	Fisher meets Feynman: score-based variational inference with a product of experts. CoRR Diana Cai, Robert M. Gower, David M. Blei, Lawrence K. Saul
2025	A	`conf`	Level Set Teleportation: An Optimization Perspective. AISTATS Aaron Mishkin, Alberto Bietti, Robert M. Gower
2025	J	`jnl`	Schedulers for Schedule-free: Theoretically inspired hyperparameters. CoRR Yuen-Man Pun, Matthew Buchholz, Robert M. Gower
2025	J	`jnl`	Tracking the Median of Gradients with a Stochastic Proximal Point Method. Trans. Mach. Learn. Res. Fabian Schaipp, Guillaume Garrigos, Umut Simsekli, Robert M. Gower
2024	J	`jnl`	A Bregman-Kaczmarz method for nonlinear systems of equations. Comput. Optim. Appl. Robert M. Gower, Dirk A. Lorenz, Maximilian Winkler
2024	A*	`conf`	Batch and match: black-box variational inference with a score-based divergence. ICML Diana Cai, Chirag Modi, Loucas Pillaud-Vivien, Charles Margossian, Robert M. Gower, David M. Blei, Lawrence K. Saul
2024	J	`jnl`	Batch and match: black-box variational inference with a score-based divergence. CoRR Diana Cai, Chirag Modi, Loucas Pillaud-Vivien, Charles C. Margossian, Robert M. Gower, David M. Blei, Lawrence K. Saul
2024	A*	`conf`	Directional Smoothness and Gradient Methods: Convergence and Adaptivity. NeurIPS Aaron Mishkin, Ahmed Khaled, Yuanhao Wang, Aaron Defazio, Robert M. Gower
2024	J	`jnl`	Directional Smoothness and Gradient Methods: Convergence and Adaptivity. CoRR Aaron Mishkin, Ahmed Khaled, Yuanhao Wang, Aaron Defazio, Robert M. Gower
2024	A*	`conf`	EigenVI: score-based variational inference with orthogonal function expansions. NeurIPS Diana Cai, Chirag Modi, Charles Margossian, Robert M. Gower, David M. Blei, Lawrence K. Saul
2024	J	`jnl`	EigenVI: score-based variational inference with orthogonal function expansions. CoRR Diana Cai, Chirag Modi, Charles C. Margossian, Robert M. Gower, David M. Blei, Lawrence K. Saul
2024	J	`jnl`	Enhancing Policy Gradient with the Polyak Step-Size Adaption. CoRR Yunxiang Li, Rui Yuan, Chen Fan, Mark Schmidt, Samuel Horváth, Robert M. Gower, Martin Takác
2024	A*	`conf`	Improving Convergence and Generalization Using Parameter Symmetries. ICLR Bo Zhao, Robert M. Gower, Robin Walters, Rose Yu
2024	J	`jnl`	Level Set Teleportation: An Optimization Perspective. CoRR Aaron Mishkin, Alberto Bietti, Robert M. Gower
2024	A*	`conf`	MoMo: Momentum Models for Adaptive Learning Rates. ICML Fabian Schaipp, Ruben Ohana, Michael Eickenberg, Aaron Defazio, Robert M. Gower
2024	J	`jnl`	SGD with Clipping is Secretly Estimating the Median Gradient. CoRR Fabian Schaipp, Guillaume Garrigos, Umut Simsekli, Robert M. Gower
2023	J	`jnl`	A Bregman-Kaczmarz method for nonlinear systems of equations. CoRR Robert M. Gower, Dirk A. Lorenz, Maximilian Winkler
2023	A*	`conf`	A Model-Based Method for Minimizing CVaR and Beyond. ICML Si Yi Meng, Robert M. Gower
2023	J	`jnl`	A Model-Based Method for Minimizing CVaR and Beyond. CoRR Si Yi Meng, Robert M. Gower
2023	J	`jnl`	A Stochastic Proximal Polyak Step Size. CoRR Fabian Schaipp, Robert M. Gower, Michael Ulbrich
2023	J	`jnl`	A Stochastic Proximal Polyak Step Size. Trans. Mach. Learn. Res. Fabian Schaipp, Robert M. Gower, Michael Ulbrich
2023	J	`jnl`	Function Value Learning: Adaptive Learning Rates Based on the Polyak Stepsize and Function Splitting in ERM. CoRR Guillaume Garrigos, Robert M. Gower, Fabian Schaipp
2023	J	`jnl`	Improving Convergence and Generalization Using Parameter Symmetries. CoRR Bo Zhao, Robert M. Gower, Robin Walters, Rose Yu
2023	A*	`conf`	Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies. ICLR Rui Yuan, Simon Shaolei Du, Robert M. Gower, Alessandro Lazaric, Lin Xiao
2023	J	`jnl`	MoMo: Momentum Models for Adaptive Learning Rates. CoRR Fabian Schaipp, Ruben Ohana, Michael Eickenberg, Aaron Defazio, Robert M. Gower
2023	A*	`conf`	Provable convergence guarantees for black-box variational inference. NeurIPS Justin Domke, Robert M. Gower, Guillaume Garrigos
2023	J	`jnl`	Provable convergence guarantees for black-box variational inference. CoRR Justin Domke, Guillaume Garrigos, Robert M. Gower
2023	J	`jnl`	SANIA: Polyak-type Optimization Framework Leads to Scale Invariant Stochastic Algorithms. CoRR Farshed Abdukhakimov, Chulu Xiang, Dmitry Kamzolov, Robert M. Gower, Martin Takác
2023	A*	`conf`	SP2 : A Second Order Stochastic Polyak Method. ICLR Shuang Li, William J. Swartworth, Martin Takác, Deanna Needell, Robert M. Gower
2023	J	`jnl`	Unified Analysis of Stochastic Gradient Methods for Composite Convex and Smooth Optimization. J. Optim. Theory Appl. Ahmed Khaled, Othmane Sebbouh, Nicolas Loizou, Robert M. Gower, Peter Richtárik
2023	A*	`conf`	Variational Inference with Gaussian Score Matching. NeurIPS Chirag Modi, Robert M. Gower, Charles Margossian, Yuling Yao, David M. Blei, Lawrence K. Saul
2023	J	`jnl`	Variational Inference with Gaussian Score Matching. CoRR Chirag Modi, Charles Margossian, Yuling Yao, Robert M. Gower, David M. Blei, Lawrence K. Saul
2022	J	`jnl`	A Statistical Linear Precoding Scheme Based on Random Iterative Method for Massive MIMO Systems. IEEE Trans. Wirel. Commun. Zheng Wang, Robert M. Gower, Cheng Zhang, Shanxiang Lyu, Yili Xia, Yongming Huang
2022	A	`conf`	A general sample complexity analysis of vanilla policy gradient. AISTATS Rui Yuan, Robert M. Gower, Alessandro Lazaric
2022	J	`jnl`	Cutting Some Slack for SGD with Adaptive Polyak Stepsizes. CoRR Robert M. Gower, Mathieu Blondel, Nidham Gazagnadou, Fabian Pedregosa
2022	J	`jnl`	Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies. CoRR Rui Yuan, Simon S. Du, Robert M. Gower, Alessandro Lazaric, Lin Xiao
2022	J	`jnl`	Randomized Iterative Methods for Low-Complexity Large-Scale MIMO Detection. IEEE Trans. Signal Process. Zheng Wang, Robert M. Gower, Yili Xia, Lanxin He, Yongming Huang
2022	J	`jnl`	RidgeSketch: A Fast Sketching Based Solver for Large Scale Ridge Regression. SIAM J. Matrix Anal. Appl. Nidham Gazagnadou, Mark Ibrahim, Robert M. Gower
2022	A	`conf`	SAN: Stochastic Average Newton Algorithm for Minimizing Finite Sums. AISTATS Jiabin Chen, Rui Yuan, Guillaume Garrigos, Robert M. Gower
2022	J	`jnl`	SP2: A Second Order Stochastic Polyak Method. CoRR Shuang Li, William J. Swartworth, Martin Takác, Deanna Needell, Robert M. Gower
2022	J	`jnl`	Sketched Newton-Raphson. SIAM J. Optim. Rui Yuan, Alessandro Lazaric, Robert M. Gower
2021	J	`jnl`	A general sample complexity analysis of vanilla policy gradient. CoRR Rui Yuan, Robert M. Gower, Alessandro Lazaric
2021	A*	`conf`	Almost sure convergence rates for Stochastic Gradient Descent and Stochastic Heavy Ball. COLT Othmane Sebbouh, Robert M. Gower, Aaron Defazio
2021	J	`jnl`	On Adaptive Sketch-and-Project for Solving Linear Systems. SIAM J. Matrix Anal. Appl. Robert M. Gower, Denali Molitor, Jacob D. Moorman, Deanna Needell
2021	J	`jnl`	SAN: Stochastic Average Newton Algorithm for Minimizing Finite Sums. CoRR Jiabin Chen, Rui Yuan, Guillaume Garrigos, Robert M. Gower
2021	A	`conf`	SGD for Structured Nonconvex Functions: Learning Rates, Minibatching and Interpolation. AISTATS Robert M. Gower, Othmane Sebbouh, Nicolas Loizou
2021	J	`jnl`	Stochastic Polyak Stepsize with a Moving Target. CoRR Robert M. Gower, Aaron Defazio, Michael G. Rabbat
2021	J	`jnl`	Stochastic quasi-gradient methods: variance reduction via Jacobian sketching. Math. Program. Robert M. Gower, Peter Richtárik, Francis R. Bach
2021	C	`conf`	The Power of Factorial Powers: New Parameter settings for (Stochastic) Optimization. ACML Aaron Defazio, Robert M. Gower
2020	J	`jnl`	A new framework for the computation of Hessians. CoRR Robert M. Gower, Margarida P. Mello
2020	J	`jnl`	Factorial Powers for Stochastic Optimization. CoRR Aaron Defazio, Robert M. Gower
2020	J	`jnl`	Fast Linear Convergence of Randomized BFGS. CoRR Dmitry Kovalev, Robert M. Gower, Peter Richtárik, Alexander Rogozin
2020	J	`jnl`	On the convergence of the Stochastic Heavy Ball Method. CoRR Othmane Sebbouh, Robert M. Gower, Aaron Defazio
2020	J	`jnl`	SGD for Structured Nonconvex Functions: Learning Rates, Minibatching and Interpolation. CoRR Robert M. Gower, Othmane Sebbouh, Nicolas Loizou
2020	J	`jnl`	Sketched Newton-Raphson. CoRR Rui Yuan, Alessandro Lazaric, Robert M. Gower
2020	J	`jnl`	Unified Analysis of Stochastic Gradient Methods for Composite Convex and Smooth Optimization. CoRR Ahmed Khaled, Othmane Sebbouh, Nicolas Loizou, Robert M. Gower, Peter Richtárik
2020	J	`jnl`	Variance-Reduced Methods for Machine Learning. CoRR Robert M. Gower, Mark Schmidt, Francis R. Bach, Peter Richtárik
2020	J	`jnl`	Variance-Reduced Methods for Machine Learning. Proc. IEEE Robert M. Gower, Mark Schmidt, Francis R. Bach, Peter Richtárik
2019	J	`jnl`	Adaptive Sketch-and-Project Methods for Solving Linear Systems. CoRR Robert M. Gower, Denali Molitor, Jacob D. Moorman, Deanna Needell
2019	A*	`conf`	Optimal Mini-Batch and Step Sizes for SAGA. ICML Nidham Gazagnadou, Robert M. Gower, Joseph Salmon
2019	J	`jnl`	Optimal mini-batch and step sizes for SAGA. CoRR Nidham Gazagnadou, Robert M. Gower, Joseph Salmon
2019	A*	`conf`	RSN: Randomized Subspace Newton. NeurIPS Robert M. Gower, Dmitry Kovalev, Felix Lieder, Peter Richtárik
2019	A*	`conf`	SGD with Arbitrary Sampling: General Analysis and Improved Rates. ICML Xun Qian, Peter Richtárik, Robert M. Gower, Alibek Sailanbayev, Nicolas Loizou, Egor Shulgin
2019	A*	`conf`	Towards closing the gap between the theory and practice of SVRG. NeurIPS Othmane Sebbouh, Nidham Gazagnadou, Samy Jelassi, Francis R. Bach, Robert M. Gower
2019	J	`jnl`	Towards closing the gap between the theory and practice of SVRG. CoRR Othmane Sebbouh, Nidham Gazagnadou, Samy Jelassi, Francis R. Bach, Robert M. Gower
2018	A*	`conf`	Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization. NeurIPS Robert M. Gower, Filip Hanzely, Peter Richtárik, Sebastian U. Stich
2018	J	`jnl`	Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization. CoRR Robert M. Gower, Filip Hanzely, Peter Richtárik, Sebastian U. Stich
2018	J	`jnl`	Greedy stochastic algorithms for entropy-regularized optimal transport problems. CoRR Brahim Khalil Abid, Robert M. Gower
2018	A	`conf`	Stochastic algorithms for entropy-regularized optimal transport problems. AISTATS Brahim Khalil Abid, Robert M. Gower
2018	A	`conf`	Tracking the gradients using the Hessian: A new look at variance reducing stochastic methods. AISTATS Robert M. Gower, Nicolas Le Roux, Francis R. Bach
2017	J	`jnl`	Randomized Quasi-Newton Updates Are Linearly Convergent Matrix Inversion Algorithms. SIAM J. Matrix Anal. Appl. Robert M. Gower, Peter Richtárik
2017	J	`jnl`	Tracking the gradients using the Hessian: A new look at variance reducing stochastic methods. CoRR Robert M. Gower, Nicolas Le Roux, Francis R. Bach
2016	J	`jnl`	Randomized Quasi-Newton Updates are Linearly Convergent Matrix Inversion Algorithms. CoRR Robert M. Gower, Peter Richtárik
2016	A*	`conf`	Stochastic Block BFGS: Squeezing More Curvature out of Data. ICML Robert M. Gower, Donald Goldfarb, Peter Richtárik
2012	J	`jnl`	A new framework for the computation of Hessians. Optim. Methods Softw. Robert M. Gower, Margarida P. Mello