Adaptively Incorporating Directional Hints into Zeroth-Order Optimization
Alexander Ryabchenko, Jian Qian, Wenlong Mou
Accepted to NeurIPS 2026
Online Imitation Learning for Stabilizing Vlasov–Poisson Plasmas
Xiaofan Xia, Qin Li, Wenlong Mou
Predicting and improving test-time scaling laws via reward tail-guided search
Muheng Li, Jian Qian, Wenlong Mou
What should post-training optimize? A test-time scaling law perspective
A decorrelation method for general regression adjustment in randomized experiments
Fangzhou Su, Wenlong Mou (equal contribution), Peng Ding, Martin J. Wainwright
Accepted to Journal of the Royal Statistical Society: Series B (JRSSB)
Provable imitation learning for control of instability in partially-observed Vlasov–Poisson equations
Reinforcement Learning with Action-Triggered Observations
Alexander Ryabchenko, Wenlong Mou
Accepted to ICML 2026
Continuous-time reinforcement learning: ellipticity enables model-free value function approximation
Wenlong Mou
Revisiting the Constant Stepsize Stochastic Approximation with Decision-Dependent Markovian Noise
Hadi Hadavi, Wenlong Mou, Sergey Samsonov, Hoi-To Wai
Is RL fine-tuning harder than regression? A PDE learning approach for diffusion models
Federated learning over physical channels: adaptive algorithms with near-optimal guarantees
Rui Zhang, Wenlong Mou (equal contribution)
Statistical guarantees for continuous-time policy evaluation: blessing of ellipticity and new tradeoffs
To bootstrap or to rollout? An optimal and adaptive interpolation
Wenlong Mou, Jian Qian (equal contribution)
On Bellman equations for continuous-time policy evaluation: discretization and approximation
Wenlong Mou, Yuhua Zhu (equal contribution)
Accepted to SIAM Journal on Mathematics of Data Science, 2025+
When is it worthwhile to jackknife? Breaking the quadratic barrier for Z-estimators
Licong Lin, Fangzhou Su, Wenlong Mou, Peng Ding, Martin J. Wainwright
Optimal oracle inequalities for solving projected fixed-point equations, with applications to policy evaluation
Wenlong Mou, Ashwin Pananjady, and Martin Wainwright
Published at Mathematics of Operations Research, 2023
Kernel-based off-policy estimation without overlap: Instance optimality beyond semiparametric efficiency
Wenlong Mou, Peng Ding, Martin Wainwright, and Peter Bartlett
Off-policy Estimation of Linear Functionals: Non-asymptotic Theory for Semi-parametric Efficiency
Wenlong Mou, Martin Wainwright, and Peter Bartlett
Optimal and Instance-dependent Guarantees for Markovian Linear Stochastic Approximation
Wenlong Mou, Ashwin Pananjady, Martin Wainwright, and Peter Bartlett
Selected as a finalist for INFORMS APS student paper competition, 2022
Extended abstract appeared at COLT 2022
Accepted to Mathematical Statistics and Learning, 2023+
A Diffusion Process Perspective on Posterior Contraction Rates for Parameters
Wenlong Mou, Nhat Ho, Martin Wainwright, Peter Bartlett, and Michael Jordan
Accepted to SIAM Journal on Mathematics of Data Science, 2023+
Optimal Variance-reduced Stochastic Approximation in Banach Spaces
Wenlong Mou, Koulik Khamaru (equal contribution), Martin Wainwright, Peter Bartlett, and Michael Jordan
When is the estimated propensity score better? High-dimensional analysis and bias correction
Fangzhou Su, Wenlong Mou (equal contribution), Peng Ding, Martin Wainwright
ROOT-SGD: Sharp Nonasymptotics and Asymptotic Efficiency in a Single Algorithm
Chris Junchi Li, Wenlong Mou (equal contribution), Martin Wainwright, and Michael Jordan
In proceedings of COLT 2022
Improved Bounds for Discretization of Langevin Diffusions: Near-optimal rates without Convexity
Wenlong Mou, Nicolas Flammarion, Martin Wainwright, and Peter Bartlett
Published at Bernoulli 28.3 (2022): 1577-1601
High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm
Wenlong Mou, Yi-An Ma (equal contribution), Martin Wainwright, Peter Bartlett, and Michael Jordan
Published at Journal of Machine Learning Research, 22(42):1-41, 2021
An Efficient Sampling Algorithm for Non-smooth Composite Potentials
Published at Journal of Machine Learning Research, to appear (2022+)
On the Sample Complexity of Reinforcement Learning with Policy Space Generalization
Wenlong Mou, Zheng Wen, Xi Chen
On Linear Stochastic Approximation: Fine-grained Polyak–Ruppert and Non-Asymptotic Concentration
Wenlong Mou, Chris Junchi Li, Martin Wainwright, Peter Bartlett, and Michael Jordan
In proceedings of COLT 2020
Sampling for Bayesian Mixture Models: MCMC with Polynomial-time Mixing
Generalization Bounds of SGLD for Non-convex Learning: Two Theoretical Viewpoints
Wenlong Mou, Liwei Wang, Xiyu Zhai, and Kai Zheng (alphabetical order)
In proceedings of COLT 2018
Dropout Training, Adaptive Regularization and Generalization Error Bounds
Wenlong Mou, Yuchen Zhou, Jun Gao, and Liwei Wang
In proceedings of ICML 2018
Differentially Private Clustering in High-dimensional Euclidean Spaces
Maria-Florina Balcan, Travis Dick, Yingyu Liang, Wenlong Mou, and Hongyang Zhang (alphabetical order)
In proceedings of ICML 2017
Collect at Once, Use Effectively: Making Non-interactive Locally Private Learning Possible
Kai Zheng, Wenlong Mou, Liwei Wang