Optimization & Decision Intelligence Group

Efficient Algorithms for a Class of Stochastic Hidden Convex Optimization and Its Applications in Network Revenue Management.

Xin Chen, Niao He, Yifan Hu, Zikun Ye.

Operations Research, 2024.

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

Semih Cayci, Niao He, R Srikant.

SIAM Journal on Optimization, 2024.

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

Semih Cayci, Niao He, R Srikant.

SIAM Journal on Mathematics of Data Science, 2024.

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

Semih Cayci, Niao He, R. Srikant.

Transactions on Machine Learning Research, 2024.

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

Liang Zhang, Bingcong Li, Kiran Koshy Thekumparampil, Sewoong Oh, Niao He.

ICML, 2024.

Truly No-Regret Learning in Constrained MDPs.

Adrian Müller, Pragnya Alatur, Volkan Cevher, Giorgia Ramponi, Niao He.

ICML, 2024.

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

Jiawei Huang, Niao He, and Andreas Krause.

ICML, 2024.

When is Mean-Field Reinforcement Learning Tractable and Relevant?

Batuhan Yardim, Artur Goldman and Niao He.

AAMAS, 2024.

Provably Learning Nash Policies in Constrained Markov Potential Games.

Pragnya Alatur, Giorgia Ramponi, Niao He, Andreas Krause.

AAMAS, 2024.

Automated Design of Affine Maximizer Mechanisms in Dynamic Settings.

Michael Curry, Vinzenz Thoma, Darshan Chakrabarti, Stephen Marcus McAleer, Christian Kroer, Tuomas Sandholm, Niao He, Sven Seuken.

AAAI, 2024.

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

Pragnya Alatur, Anas Barakat, and Niao He.

CDC, 2024.

Parameter-Agnostic Optimization under Relaxed Smoothness.

Florian Hübler, Junchi Yang, Xiang Li, Niao He.

AISTATS, 2024.

On the Statistical Efficiency of Mean Field RL with General Function Approximation.

Jiawei Huang, Batuhan Yardim, and Niao He.

AISTATS, 2024.

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

Siqi Zhang, Yifan Hu, Liang Zhang, Niao He.

AISTATS, 2024.

Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence.

Ilyas Fatkhullin and Niao He.

AISTATS, 2024.

Independent Learning in Constrained Markov Potential Games.

Philip Jordan, Anas Barakat, and Niao He.

AISTATS, 2024.

Momentum-Based Policy Gradient with Second-Order Information.

Saber Salehkaleybar, Sadegh Khorasani, Negar Kiyavash, Niao He, Patrick Thiran.

Transactions of Machine Learning Research, 2024.

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

Jun Song, Niao He, Lijun Ding, Chaoyue Zhao

Transactions of Machine Learning Research, 2023.

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

Cayci, Semih, Siddhartha Satpathi, Niao He, and R. Srikant

IEEE Transactions on Automatic Control, 2023.

A Discrete-time Switching System Analysis of Q-learning.

Donghwan Lee, Jianghai Hu, and Niao He

SIAM Journal on Control and Optimization, 2023.

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

Liang Zhang, Junchi Yang, Amin Karbasi, Niao He.

NeurIPS, 2023. (Spotlight)

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

Junchi Yang, Xiang Li, Ilyas Fatkhullin, Niao He.

NeurIPS, 2023.

Robust Knowledge Transfer in Tiered Reinforcement Learning.

Jiawei Huang, Niao He.

NeurIPS, 2023.

On Imitation in Mean-field Games.

Giorgia Ramponi, Pavel Kolev, Olivier Pietquin, Niao He, Mathieu Laurière, Matthieu Geist.

NeurIPS, 2023.

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

Xiang Li, Junchi Yang, Niao He.

ICLR, 2023.

Policy mirror ascent for efficient and independent learning in mean field games.

Batuhan Yardim, Semih Cayci, Matthieu Geist, Niao He.

ICML, 2023.

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

Anas Barakat, Ilyas Fatkhullin, Niao He.

ICML, 2023.

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

Ilyas Fatkhullin, Anas Barakat, Anastasia Kireeva, Niao He.

ICML, 2023.

Kernel Conditional Moment Constraints for Confounding Robust Inference.

Kei Ishikawa and Niao He.

AISTATS, 2023.

Learning to Optimize for Stochastic Dominance Constraints.

Hanjun Dai, Yuan Xue, Niao He, Bethany Wang, Na Li, Dale Schuurmans, Bo Dai.

AISTATS, 2023.

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

Ilyas Fatkhullin, Jalal Etesami, Niao He, Negar Kiyavash.

NeurIPS, 2022.

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

Liang Zhang, Kiran Koshy Thekumparampil, Sewoong Oh, Niao He.

NeurIPS, 2022.

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

Junchi Yang, Xiang Li, Niao He.

NeurIPS, 2022.

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

Saeed Masiha, Saber Salehkaleybar, Niao He, Negar Kiyavash, Patrick Thiran.

NeurIPS, 2022.

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

Ahmet Alacaoglu, Luca Viano, Niao He, Volkan Cevher.

ICML, 2022.

Efficient Algorithms for Minimizing Compositions of Convex Functions and Random Functions and Its Applications in Network Revenue Management.

Xin Chen, Niao He, Yifan Hu, Zikun Ye.

arXiv preprint arXiv:2205.01774, 2022.

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

Junchi Yang, Antonio Orvieto, Aurelien Lucchi, Niao He.

AISTATS, 2022.

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

Kiran Koshy Thekumparampil, Niao He, Sewoong Oh.

AISTATS, 2022 (Oral).

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

Yifan Hu, Xin Chen, Niao He.

NeurIPS, 2021.

The Complexity of Nonconvex-Strongly-Concave Minimax Optimization.

Siqi Zhang, Junchi Yang, Cristóbal Guzmán, Negar Kiyavash, and Niao He.

Uncertainty in Artificial Intelligence (UAI), 2021.

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

Cayci, Semih, Siddhartha Satpathi, Niao He, and R. Srikant

ICML 2021 workshop on Overparametrization: Pitfalls and Opportunities. arXiv preprint arXiv:2103.01391, 2021.

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

Yingxiang Yang, Negar Kiyavash, Le Song, and Niao He

NeurIPS, 2020. (Spotlight)

A Catalyst Framework for Minimax Optimization

Junchi Yang, Siqi Zhang, Negar Kiyavash, and Niao He

NeurIPS, 2020.

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

Donghwan Lee and Niao He

NeurIPS, 2020.

Provably-Efficient Double Q-Learning

Wentao Weng, Harsh Gupta, Niao He, Lei Ying, and R Srikant

NeurIPS, 2020.

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

Junchi Yang, Negar Kiyavash, and Niao He

NeurIPS, 2020.

Biased Stochastic Gradient Descent for Conditional Stochastic Optimization

Yifan Hu, Siqi Zhang, Xin Chen, and Niao He

NeurIPS, 2020.

Periodic Q-Learning

Donghwan Lee and Niao He

Learning for Dynamics and Control (L4DC), 2020.

Quadratic Decomposable Submodular Function Minimization: Theory and Practice

Pan Li, Niao He, Olgica Milenkovic

Journal of Machine Learning Research, 2020

Sample Complexity of Sample Average Approximation for Conditional Stochastic Optimization

Yifan Hu, Xin Chen, and Niao He

SIAM Journal on Optimization, 2020.

Optimization for Reinforcement Learning: From Single Agent to Cooperative Agents

Donghwan Lee, Niao He, Parameswaran Kamalaruban, Volkan Cevher

IEEE Signal Processing Magazine, Volume: 37, Issue: 3, May 2020.

Bregman Augmented Lagrangian and Its Acceleration

Shen Yan and Niao He

arXiv preprint arXiv:2002.06315, 2020.

Point Process Estimation with Mirror Prox Algorithms

Niao He, Zaid Harchaoui, Yichen Wang, and Le Song

Applied Mathematics and Optimization, 2019.

Learning Positive Functions with Pseudo Mirror Descent

Yingxiang Yang, Haoxiang Wang, Negar Kiyavash, and Niao He

Neural Information Processing Systems (NeurIPS), 2019. (Spotlight)

Exponential Family Estimation via Adversarial Dynamics Embedding

Bo Dai, Zhen Liu, Hanjun Dai, Niao He, Arthur Gretton, Le Song, and Dale Schuurmans

Neural Information Processing Systems (NeurIPS), 2019.

Target-Based Temporal Difference Learning

Donghwan Lee, Niao He

International Conference on Machine Learning (ICML), 2019.

Optimization and Learning Algorithms for Stochastic and Adversarial Power Control

Harsh Gupta, Niao He, and R. Srikant

The 17th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt), 2019.

Kernel Exponential Family Estimation via Doubly Dual Embedding

Bo Dai, Hanjun Dai, Arthur Gretton, Le Song, Dale Schuurmans, Niao He

Artificial Intelligence and Statistics (AISTATS), 2019.

Stochastic Primal-Dual Q-Learning Algorithms for Discounted MDPs

Donghwan Lee, Niao He

American Control Conference (ACC), 2019.

Dynamic Programming for Stochastic Control Systems with Jointly Discrete and Continuous State-Spaces

Donghwan Lee, Niao He, Jianghai Hu

American Control Conference (ACC), 2019.

On the Convergence Rate of Stochastic Mirror Descent for Nonsmooth Nonconvex Optimization

Siqi Zhang, Niao He

arXiv preprint arXiv:1806.04781.

Coupled Variational Bayes via Optimization Embedding

Bo Dai, Hanjun Dai, Niao He, Weiyang Liu, Zhen Liu, Jianshu Chen, Lin Xiao, Le Song

Neural Information Processing Systems (NIPS), 2018.

Quadratic Decomposable Submodular Function Minimization

Pan Li, Niao He, Olgica Milenkovic

Neural Information Processing Systems (NIPS), 2018.

Predictive Approximate Bayesian Computation via Saddle Points

Yingxiang Yang, Bo Dai, Negar Kiyavash, Niao He

Neural Information Processing Systems (NIPS), 2018.

SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation

Bo Dai, Albert Shaw, Lihong Li, Lin Xiao, Niao He, Zhen Liu, Jianshu Chen, Le Song

International Conference on Machine Learning (ICML), 2018.

Boosting The Actor With Dual Critic

Bo Dai, Albert Shaw, Niao He, Lihong Li, and Le Song

International Conference on Learning Representations (ICLR), 2018.

Online Learning for Multivariate Hawkes Processes

Yingxiang Yang, Jalal Etsami, Niao He, and Negar Kiyavash

Neural Information Processing Systems (NIPS), 2017.

Smoothed Dual Embedding Control

Bo Dai, Albert Shaw, Lihong Li, Lin Xiao, Niao He, Jianshu Chen, Le Song

NIPS Deep Reinforcement Learning Symposium, 2017.

Stochastic Generative Hashing

Bo Dai, Ruiqi Guo, Sanjiv Kumar, Niao He, Le Song

International Conference on Machine Learning (ICML), 2017.

Learning from Conditional Distributions via Dual Kernel Embeddings

Bo Dai, Niao He, Yunpeng Pan, Byron Boots, Le Song

Artificial Intelligence and Statistics (AISTATS), 2017.

Provable Bayesian Inference via Particle Mirror Descent

Bo Dai, Niao He, Hanjun Dai, and Le Song

Artificial Intelligence and Statistics (AISTATS), 2016.

Saddle Point Techniques in Convex Composite and Error-in-Measurement Optimization

Niao He

Georgia Institute of Technology, November 2015.

Mirror Prox Algorithm for Multi-Term Composite Minimization and Semi-Separable Problems

Niao He, Anatoli Juditsky, and Arkadi Nemirovski

Journal of Computational Optimization and Applications, 61(2), 275-319, 2015.

Semi-proximal Mirror-Prox for Nonsmooth Composite Minimization

Niao He and Zaid Harchaoui

Neural Information Processing Systems (NIPS), 2015.

Time-sensitive Recommendation From Recurrent User Activities

Nan Du, Yichen Wang, Niao He, and Le Song

Neural Information Processing Systems (NIPS), 2015.

Stochastic Semi-Proximal Mirror Prox

Niao He and Zaid Harchaoui

NIPS 8th International Workshop on Optimization for Machine Learning, 2015.

Scalable Kernel Methods via Doubly Stochastic Gradients

Bo Dai, Bo Xie, Niao He, Yingyu Liang, Anant Raj, Maria-Florina Balcan, and Le Song

Neural Information Processing Systems (NIPS), 2014.

Stochastic Alternating Direction Method of Multipliers

Hua Ouyang, Niao He, Long Tran, and Alexander Gray

International Conference on Machine Learning (ICML), 2013.

Selected Publications

Filter by type:

Efficient Algorithms for a Class of Stochastic Hidden Convex Optimization and Its Applications in Network Revenue Management.

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

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

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

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

Truly No-Regret Learning in Constrained MDPs.

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

When is Mean-Field Reinforcement Learning Tractable and Relevant?

Provably Learning Nash Policies in Constrained Markov Potential Games.

Automated Design of Affine Maximizer Mechanisms in Dynamic Settings.

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

Parameter-Agnostic Optimization under Relaxed Smoothness.

On the Statistical Efficiency of Mean Field RL with General Function Approximation.

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

Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence.

Independent Learning in Constrained Markov Potential Games.

Momentum-Based Policy Gradient with Second-Order Information.

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

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

A Discrete-time Switching System Analysis of Q-learning.

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

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

Robust Knowledge Transfer in Tiered Reinforcement Learning.

On Imitation in Mean-field Games.

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

Policy mirror ascent for efficient and independent learning in mean field games.

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

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

Kernel Conditional Moment Constraints for Confounding Robust Inference.

Learning to Optimize for Stochastic Dominance Constraints.

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

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

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

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

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

Efficient Algorithms for Minimizing Compositions of Convex Functions and Random Functions and Its Applications in Network Revenue Management.

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

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

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

The Complexity of Nonconvex-Strongly-Concave Minimax Optimization.

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

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

A Catalyst Framework for Minimax Optimization

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

Provably-Efficient Double Q-Learning

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

Biased Stochastic Gradient Descent for Conditional Stochastic Optimization

Periodic Q-Learning

Quadratic Decomposable Submodular Function Minimization: Theory and Practice

Sample Complexity of Sample Average Approximation for Conditional Stochastic Optimization

Optimization for Reinforcement Learning: From Single Agent to Cooperative Agents

Bregman Augmented Lagrangian and Its Acceleration

Point Process Estimation with Mirror Prox Algorithms

Learning Positive Functions with Pseudo Mirror Descent

Exponential Family Estimation via Adversarial Dynamics Embedding

Target-Based Temporal Difference Learning

Optimization and Learning Algorithms for Stochastic and Adversarial Power Control

Kernel Exponential Family Estimation via Doubly Dual Embedding

Stochastic Primal-Dual Q-Learning Algorithms for Discounted MDPs

Dynamic Programming for Stochastic Control Systems with Jointly Discrete and Continuous State-Spaces

On the Convergence Rate of Stochastic Mirror Descent for Nonsmooth Nonconvex Optimization

Coupled Variational Bayes via Optimization Embedding

Quadratic Decomposable Submodular Function Minimization

Predictive Approximate Bayesian Computation via Saddle Points

SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation

Boosting The Actor With Dual Critic

Online Learning for Multivariate Hawkes Processes

Smoothed Dual Embedding Control

Stochastic Generative Hashing

Learning from Conditional Distributions via Dual Kernel Embeddings

Provable Bayesian Inference via Particle Mirror Descent

Saddle Point Techniques in Convex Composite and Error-in-Measurement Optimization

Mirror Prox Algorithm for Multi-Term Composite Minimization and Semi-Separable Problems

Semi-proximal Mirror-Prox for Nonsmooth Composite Minimization

Time-sensitive Recommendation From Recurrent User Activities

Stochastic Semi-Proximal Mirror Prox

Scalable Kernel Methods via Doubly Stochastic Gradients

Stochastic Alternating Direction Method of Multipliers