Niao He

Patrick Thiran

Trans. Mach. Learn. Res., 2024

Finite-Time Analysis of Entropy-Regularized Neural Natural Actor-Critic Algorithm.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2024

Finite-Time Analysis of Natural Actor-Critic for POMDPs.

[BibT_eX]

[DOI]

SIAM J. Math. Data Sci., 2024

Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation.

[BibT_eX]

[DOI]

SIAM J. Optim., 2024

On the Crucial Role of Initialization for Matrix Factorization.

[BibT_eX]

[DOI]

CoRR, 2024

Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems.

[BibT_eX]

[DOI]

Bingcong Li

CoRR, 2024

From Gradient Clipping to Normalization for Heavy Tailed SGD.

[BibT_eX]

[DOI]

Florian Hübler

CoRR, 2024

Exploiting Approximate Symmetry for Efficient Multi-Agent Reinforcement Learning.

[BibT_eX]

[DOI]

Batuhan Yardim

CoRR, 2024

Multi-level Monte-Carlo Gradient Methods for Stochastic Optimization with Biased Oracles.

[BibT_eX]

[DOI]

CoRR, 2024

Independent Policy Mirror Descent for Markov Potential Games: Scaling to Large Number of Players.

[BibT_eX]

[DOI]

Pragnya Alatur

Anas Barakat

CoRR, 2024

Complexity of Minimizing Projected-Gradient-Dominated Functions with Stochastic First-order Oracles.

[BibT_eX]

[DOI]

CoRR, 2024

Learning to Steer Markovian Agents under Model Uncertainty.

[BibT_eX]

[DOI]

CoRR, 2024

Achieving Near-Optimal Convergence for Distributed Minimax Optimization with Adaptive Stepsizes.

[BibT_eX]

[DOI]

CoRR, 2024

A Hessian-Aware Stochastic Differential Equation for Modelling SGD.

[BibT_eX]

[DOI]

CoRR, 2024

Primal Methods for Variational Inequality Problems with Functional Constraints.

[BibT_eX]

[DOI]

Michael Muehlebach

CoRR, 2024

Stochastic Optimization under Hidden Convexity.

[BibT_eX]

[DOI]

Yifan Hu

CoRR, 2024

DPZero: Private Fine-Tuning of Language Models without Backpropagation.

[BibT_eX]

[DOI]

Bingcong Li

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Truly No-Regret Learning in Constrained MDPs.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL.

[BibT_eX]

[DOI]

Jiawei Huang

Andreas Krause

Proceedings of the Forty-first International Conference on Machine Learning, 2024

When is Mean-Field Reinforcement Learning Tractable and Relevant?

[BibT_eX]

[DOI]

Batuhan Yardim

Artur Goldman

Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems, 2024

Provably Learning Nash Policies in Constrained Markov Potential Games.

[BibT_eX]

[DOI]

Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems, 2024

Generalization Bounds of Nonconvex-(Strongly)-Concave Stochastic Minimax Optimization.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

Independent Learning in Constrained Markov Potential Games.

[BibT_eX]

[DOI]

Philip Jordan

Anas Barakat

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

Parameter-Agnostic Optimization under Relaxed Smoothness.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

On the Statistical Efficiency of Mean-Field Reinforcement Learning with General Function Approximation.

[BibT_eX]

[DOI]

Jiawei Huang

Batuhan Yardim

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

Automated Design of Affine Maximizer Mechanisms in Dynamic Settings.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

A Discrete-Time Switching System Analysis of Q-Learning.

[BibT_eX]

[DOI]

Jianghai Hu

SIAM J. Control. Optim., June, 2023

Sample Complexity and Overparameterization Bounds for Temporal-Difference Learning With Neural Network Approximation.

[BibT_eX]

[DOI]

IEEE Trans. Autom. Control., May, 2023

Provably Convergent Policy Optimization via Metric-aware Trust Region Methods.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2023

Learning Best Response Policies in Dynamic Auctions via Deep Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, 2023

Efficiently Escaping Saddle Points for Non-Convex Policy Optimization.

[BibT_eX]

[DOI]

Matthias Grossglauser

CoRR, 2023

DPZero: Dimension-Independent and Differentially Private Zeroth-Order Optimization.

[BibT_eX]

[DOI]

CoRR, 2023

A Convex Framework for Confounding Robust Inference.

[BibT_eX]

[DOI]

Kei Ishikawa

Takafumi Kanamori

CoRR, 2023

Cancellation-Free Regret Bounds for Lagrangian Approaches in Constrained Markov Decision Processes.

[BibT_eX]

[DOI]

CoRR, 2023

Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

On Imitation in Mean-field Games.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Robust Knowledge Transfer in Tiered Reinforcement Learning.

[BibT_eX]

[DOI]

Jiawei Huang

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space.

[BibT_eX]

[DOI]

Anas Barakat

Proceedings of the International Conference on Machine Learning, 2023

TiAda: A Time-scale Adaptive Algorithm for Nonconvex Minimax Optimization.

[BibT_eX]

[DOI]

Xiang Li

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity.

[BibT_eX]

[DOI]

Proceedings of the 62nd IEEE Conference on Decision and Control, 2023

Kernel Conditional Moment Constraints for Confounding Robust Inference.

[BibT_eX]

[DOI]

Kei Ishikawa

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

Learning to Optimize with Stochastic Dominance Constraints.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

Learning to Optimize with Stochastic Dominance Constraints.

[BibT_eX]

[DOI]

CoRR, 2022

Uniform Convergence and Generalization for Nonconvex Stochastic Minimax Problems.

[BibT_eX]

[DOI]

CoRR, 2022

Stochastic Second-Order Methods Provably Beat SGD For Gradient-Dominated Functions.

[BibT_eX]

[DOI]

CoRR, 2022

Adaptive Momentum-Based Policy Gradient with Second-Order Information.

[BibT_eX]

[DOI]

CoRR, 2022

Learning to Control Partially Observed Systems with Finite Memory.

[BibT_eX]

[DOI]

CoRR, 2022

Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimization.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Nest Your Adaptive Algorithm for Parameter-Agnostic Nonconvex Minimax Optimization.

[BibT_eX]

[DOI]

Xiang Li

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Functions.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Sharp Analysis of Stochastic Optimization under Global Kurdyka-Lojasiewicz Inequality.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

A Natural Actor-Critic Framework for Zero-Sum Markov Games.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Faster Single-loop Algorithms for Minimax Optimization without Strong Concavity.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

Lifted Primal-Dual Method for Bilinearly Coupled Smooth Minimax Optimization.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation.

[BibT_eX]

[DOI]

CoRR, 2021

Simulation Studies on Deep Reinforcement Learning for Building Control with Human Interaction.

[BibT_eX]

[DOI]

CoRR, 2021

Sample Complexity and Overparameterization Bounds for Projection-Free Neural TD Learning.

[BibT_eX]

[DOI]

CoRR, 2021

The complexity of nonconvex-strongly-concave minimax optimization.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, 2021

On the Bias-Variance-Cost Tradeoff of Stochastic Optimization.

[BibT_eX]

[DOI]

Yifan Hu

Xin Chen

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

Optimization for Reinforcement Learning: From a single agent to cooperative agents.

[BibT_eX]

[DOI]

Parameswaran Kamalaruban

Volkan Cevher

IEEE Signal Process. Mag., 2020

Sample Complexity of Sample Average Approximation for Conditional Stochastic Optimization.

[BibT_eX]

[DOI]

Yifan Hu

Xin Chen

SIAM J. Optim., 2020

Quadratic Decomposable Submodular Function Minimization: Theory and Practice.

[BibT_eX]

[DOI]

Pan Li

Olgica Milenkovic

J. Mach. Learn. Res., 2020

Provably-Efficient Double Q-Learning.

[BibT_eX]

[DOI]

CoRR, 2020

Biased Stochastic Gradient Descent for Conditional Stochastic Optimization.

[BibT_eX]

[DOI]

CoRR, 2020

Global Convergence and Variance-Reduced Optimization for a Class of Nonconvex-Nonconcave Minimax Problems.

[BibT_eX]

[DOI]

Negar Kiyavash

CoRR, 2020

A Catalyst Framework for Minimax Optimization.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

The Devil is in the Detail: A Framework for Macroscopic Prediction via Microscopic Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Global Convergence and Variance Reduction for a Class of Nonconvex-Nonconcave Minimax Problems.

[BibT_eX]

[DOI]

Negar Kiyavash

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

The Mean-Squared Error of Double Q-Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Biased Stochastic First-Order Methods for Conditional Stochastic Optimization and Applications in Meta Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

A Unified Switching System Perspective and Convergence Analysis of Q-Learning Algorithms.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Periodic Q-Learning.

[BibT_eX]

[DOI]

Proceedings of the 2nd Annual Conference on Learning for Dynamics and Control, 2020

2019

A Unified Switching System Perspective and O.D.E. Analysis of Q-Learning Algorithms.

[BibT_eX]

[DOI]

CoRR, 2019

Optimization and Learning Algorithms for Stochastic and Adversarial Power Control.

[BibT_eX]

[DOI]

Harsh Gupta

Proceedings of the International Symposium on Modeling and Optimization in Mobile, 2019

Learning Positive Functions with Pseudo Mirror Descent.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Exponential Family Estimation via Adversarial Dynamics Embedding.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Target-Based Temporal-Difference Learning.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

Dynamic Programming for POMDP with Jointly Discrete and Continuous State-Spaces.

[BibT_eX]

[DOI]

Jianghai Hu

Proceedings of the 2019 American Control Conference, 2019

Stochastic Primal-Dual Q-Learning Algorithm For Discounted MDPs.

[BibT_eX]

[DOI]

Proceedings of the 2019 American Control Conference, 2019

Kernel Exponential Family Estimation via Doubly Dual Embedding.

[BibT_eX]

[DOI]

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018

Predictive Approximate Bayesian Computation via Saddle Points.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Quadratic Decomposable Submodular Function Minimization.

[BibT_eX]

[DOI]

Pan Li

Olgica Milenkovic

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Coupled Variational Bayes via Optimization Embedding.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation.

[BibT_eX]

[DOI]

Proceedings of the 35th International Conference on Machine Learning, 2018

Boosting the Actor with Dual Critic.

[BibT_eX]

[DOI]

Proceedings of the 6th International Conference on Learning Representations, 2018

2017

Smoothed Dual Embedding Control.

[BibT_eX]

[DOI]

CoRR, 2017

Online Learning for Multivariate Hawkes Processes.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Stochastic Generative Hashing.

[BibT_eX]

[DOI]

Proceedings of the 34th International Conference on Machine Learning, 2017

Learning from Conditional Distributions via Dual Embeddings.

[BibT_eX]

[DOI]

Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 2017

2016

Fast and Simple Optimization for Poisson Likelihood Models.

[BibT_eX]

[DOI]

CoRR, 2016

Learning from Conditional Distributions via Dual Kernel Embeddings.

[BibT_eX]

[DOI]

CoRR, 2016

Provable Bayesian Inference via Particle Mirror Descent.

[BibT_eX]

[DOI]

Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, 2016

2015

Scalable Bayesian Inference via Particle Mirror Descent.

[BibT_eX]

[DOI]

CoRR, 2015

Mirror Prox algorithm for multi-term composite minimization and semi-separable problems.

[BibT_eX]

[DOI]

Anatoli B. Juditsky

Arkadi Nemirovski

Comput. Optim. Appl., 2015

Semi-Proximal Mirror-Prox for Nonsmooth Composite Minimization.

[BibT_eX]

[DOI]

Zaïd Harchaoui

Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Time-Sensitive Recommendation From Recurrent User Activities.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

2014

Scalable Kernel Methods via Doubly Stochastic Gradients.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

2013

Mirror Prox Algorithm for Multi-Term Composite Minimization and Alternating Directions.

[BibT_eX]

[DOI]

Anatoli B. Juditsky

Arkadi Nemirovski

CoRR, 2013

Stochastic Alternating Direction Method of Multipliers.

[BibT_eX]

[DOI]

Proceedings of the 30th International Conference on Machine Learning, 2013

2012

Stochastic ADMM for Nonsmooth Optimization

[BibT_eX]

[DOI]

Hua Ouyang