Selected publications

A Hessian-aware stochastic differential equation for modelling SGD

Xiang Li, Zebang Shen, Liang Zhang, Niao He · Mathematical Programming, accepted, 2026

On the Benefits of Weight Normalization for Overparameterized Matrix Sensing

Yudong Wei, Liang Zhang, Bingcong Li, Niao He · ICLR 2026

Landing with the Score: Riemannian Optimization through Denoising

Andrey Kharitenko, Zebang Shen, Riccardo De Santi, Niao He, Florian Doerfler · ICLR 2026

A Schrodinger Eigenfunction Method for Long-Horizon Stochastic Optimal Control

Louis Claeys, Artur Goldman, Zebang Shen, Niao He · ICLR 2026

When Scores Learn Geometry: Rate Separations under the Manifold Hypothesis

Xiang Li, Zebang Shen, Ya-Ping Hsieh, Niao He · ICLR 2026

Minima Selection in Stochastic Optimization: A Long-Time, Small-Stepsize Perspective

Xiang Li, Zebang Shen, Ya-Ping Hsieh, Niao He · Preprint, 2026

Hyper-Gradient Methods for Bilevel Optimization with Manifold Lower-level Solution Set

Saeed Masiha, Zebang Shen, Negar Kiyavash, Niao He · Preprint, 2026

PoLAR: Polar-Decomposed Low-Rank Adapter Representation

Kai Lion, Liang Zhang, Bingcong Li, Niao He · NeurIPS 2025

Zeroth-Order Optimization Finds Flat Minima

Liang Zhang, Bingcong Li, Kiran Thekumparampil, Sewoong Oh, Michael Muehlebach, Niao He · NeurIPS 2025

AmorLIP: Efficient Language-Image Pretraining via Amortization

Haotian Sun, Yitong Li, Yuchen Zhuang, Niao He, Hanjun Dai, Bo Dai · NeurIPS 2025

Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning

Riccardo De Santi, Marin Vlastelica, Ya-Ping Hsieh, Zebang Shen, Niao He, Andreas Krause · NeurIPS 2025

Scalable Neural Incentive Design with Parameterized Mean-Field Approximation

Nathan Corecco, Batuhan Yardim, Vinzenz Thoma, Zebang Shen, Niao He · NeurIPS 2025

Natural Gradient VI in Non-Conjugate Models

Fangyuan Sun, Ilyas Fatkhullin, Niao He · NeurIPS 2025

A Variational Inequality Approach to Independent Learning in Static Mean-Field Games

Batuhan Yardim, Semih Cayci, Niao He · ACM/IMS Journal of Data Science, 2025

Primal Methods for Variational Inequality Problems with Functional Constraints

Liang Zhang, Niao He, Michael Muehlebach · Mathematical Programming, 2025

Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity and Last-Iterate Convergence

Jiduan Wu, Anas Barakat, Ilyas Fatkhullin, Niao He · SIAM Journal on Control and Optimization, 2025

Stochastic Optimization under Hidden Convexity

Ilyas Fatkhullin, Niao He, Yifan Hu · SIAM Journal on Optimization, 2025

EF21 with Bells & Whistles: Six Algorithmic Extensions of Modern Error Feedback

Ilyas Fatkhullin, Igor Sokolov, Eduard Gorbunov, Zhize Li, Peter Richtárik · Journal of Machine Learning Research, 2025

On the Crucial Role of Initialization for Matrix Factorization

Bingcong Li, Liang Zhang, Aryan Mokhtari, Niao He · ICLR, 2025

Learning to Steer Markovian Agents under Model Uncertainty

Jiawei Huang, Vinzenz Thoma, Zebang Shen, Heinrich H Nax, Niao He · ICLR, 2025

From Gradient Clipping to Normalization for Heavy Tailed SGD

Florian Hubler, Ilyas Fatkhullin, Niao He · AISTATS, 2025

Steering No-Regret Agents in MFGs under Model Uncertainty

Leo Widmer, Jiawei Huang, Niao He · AISTATS, 2025

Efficiently Escaping Saddle Points for Policy Optimization

Mohammadsadegh Khorasani, Saber Salehkaleybar, Negar Kiyavash, Niao He, Matthias Grossglauser · UAI, 2025

Exploiting Approximate Symmetry for Efficient Multi-Agent Reinforcement Learning

Batuhan Yardim, Niao He · L4DC, 2025. (Best Paper Finalist)

Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective

Jiawei Huang, Bingcong Li, Christoph Dann, Niao He · ICML, 2025

Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning

Riccardo De Santi, Marin Vlastelica, Ya-Ping Hsieh, Zebang Shen, Niao He, Andreas Krause · GenBio Workshop at ICML, 2025. (Oral)

Policy Design in Long-Run Welfare Dynamics

Jiduan Wu, Rediet Abebe, Moritz Hardt, Ana-Andreea Stoica · ICLR, 2025

Provable Maximum Entropy Manifold Exploration via Diffusion Models

Riccardo De Santi, Marin Vlastelica, Ya-Ping Hsieh, Zebang Shen, Niao He, Andreas Krause · ICML, 2025

Safe-EF: Error Feedback for Nonsmooth Constrained Optimization

Rustem Islamov, Yarden As, Ilyas Fatkhullin · ICML, 2025

Best of Both Worlds: Regret Minimization versus Minimax Play

Adrian Müller, Jon Schneider, Stratis Skoulakis, Luca Viano, Volkan Cevher · ICML, 2025

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

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

Bingcong Li, Liang Zhang, Niao He · NeurIPS, 2024

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

Yan Huang, Xiang Li, Yipeng Shen, Niao He, Jinming Xu · NeurIPS, 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

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

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

Sample Complexity of Sample Average Approximation for Conditional Stochastic Optimization

Yifan Hu, Xin Chen, and Niao He · SIAM Journal on Optimization, 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

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

Donghwan Lee, Niao He, Jianghai Hu · American Control Conference (ACC), 2019

Stochastic Primal-Dual Q-Learning Algorithms for Discounted MDPs

Donghwan Lee, Niao He · American Control Conference (ACC), 2019

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