53 citations · 177 across the 34 of their papers we have counts for
35 papers
GAV: A scientific experimentation environment for PDE agents
Muheng Li, Wenlong Mou
Reliable feedback is essential for coding agents to develop programs for partial differential equations (PDEs). Yet evaluating these programs on new PDE problems often requires exp…
A Latent Distribution Perspective on Evaluating and Improving Latent Generative Models
Xianghong Fang, Wenjie Shu, Tongda Xu +3
In latent generative models, reconstruction quality is often assumed to correlate with generative performance. However, reconstruction FID (rFID) can exhibit weak or even negative…
Adaptively Incorporating Directional Hints into Zeroth-Order Optimization
Alexander Ryabchenko, Jian Qian, Wenlong Mou
We study zeroth-order optimization of non-convex functions with the aid of directional hints, which are cheap but potentially inaccurate approximations of the true gradient directi…
What should post-training optimize? A test-time scaling law perspective
Muheng Li, Jian Qian, Wenlong Mou
Large language models are increasingly deployed with test-time strategies: sample responses, score them with a reward model or verifier, and return the best. This deployment ru…
Provable imitation learning for control of instability in partially-observed Vlasov--Poisson equations
Xiaofan Xia, Qin Li, Wenlong Mou
We consider the stabilization of Vlasov--Poisson plasma dynamics, a central control problem in nuclear fusion. Our focus is the gap between what an ideal controller would use and w…
Revisiting the Constant Stepsize Stochastic Approximation with Decision-Dependent Markovian Noise
Hadi Hadavi, Wenlong Mou, Sergey Samsonov +1
We revisit the convergence analysis of constant stepsize stochastic approximation (SA) with decision-dependent Markovian noise, with a focus on characterizing the stationary bias a…
Continuous-time reinforcement learning: ellipticity enables model-free value function approximation
Wenlong Mou
We study off-policy reinforcement learning for controlling continuous-time Markov diffusion processes with discrete-time observations and actions. We consider model-free algorithms…
Predicting and improving test-time scaling laws via reward tail-guided search
Muheng Li, Jian Qian, Wenlong Mou
Test-time scaling has emerged as a critical avenue for enhancing the reasoning capabilities of Large Language Models (LLMs). Though the straight-forward ''best-of-'' (BoN) strat…
Reinforcement Learning with Action-Triggered Observations
Alexander Ryabchenko, Wenlong Mou
We introduce Action-Triggered Sporadically Traceable Markov Decision Processes (ATST-MDPs), a reinforcement learning framework for partial observability in which full state observa…
Federated learning over physical channels: adaptive algorithms with near-optimal guarantees
Rui Zhang, Wenlong Mou
In federated learning, communication cost can be significantly reduced by transmitting the information over the air through physical channels. In this paper, we propose a new class…
Is RL fine-tuning harder than regression? A PDE learning approach for diffusion models
Wenlong Mou
We study the problem of learning the optimal control policy for fine-tuning a given diffusion process, using general value function approximation. We develop a new class of algorit…
Statistical guarantees for continuous-time policy evaluation: blessing of ellipticity and new tradeoffs
Wenlong Mou
We study the estimation of the value function for continuous-time Markov diffusion processes using a single, discretely observed ergodic trajectory. Our work provides non-asymptoti…
To bootstrap or to rollout? An optimal and adaptive interpolation
Wenlong Mou, Jian Qian
Bootstrapping and rollout are two fundamental principles for value function estimation in reinforcement learning (RL). We introduce a novel class of Bellman operators, called subgr…
When is it worthwhile to jackknife? Breaking the quadratic barrier for Z-estimators
Licong Lin, Fangzhou Su, Wenlong Mou +2
Resampling methods are especially well-suited to inference with estimators that provide only "black-box'' access. Jackknife is a form of resampling, widely used for bias correction…
On Bellman equations for continuous-time policy evaluation I: discretization and approximation
Wenlong Mou, Yuhua Zhu
We study the problem of computing the value function from a discretely-observed trajectory of a continuous-time diffusion process. We develop a new class of algorithms based on eas…
A decorrelation method for general regression adjustment in randomized experiments
Fangzhou Su, Wenlong Mou, Peng Ding +1
We study regression adjustment with general function class approximations for estimating the average treatment effect in the design-based setting. Standard regression adjustment in…
When is the estimated propensity score better? High-dimensional analysis and bias correction
Fangzhou Su, Wenlong Mou, Peng Ding +1
Anecdotally, using an estimated propensity score is superior to the true propensity score in estimating the average treatment effect based on observational data. However, this clai…
Kernel-based off-policy estimation without overlap: Instance optimality beyond semiparametric efficiency
Wenlong Mou, Peng Ding, Martin J. Wainwright +1
We study optimal procedures for estimating a linear functional based on observational data. In many problems of this kind, a widely used assumption is strict overlap, i.e., uniform…
Off-policy estimation of linear functionals: Non-asymptotic theory for semi-parametric efficiency
Wenlong Mou, Martin J. Wainwright, Peter L. Bartlett
The problem of estimating a linear functional based on observational data is canonical in both the causal inference and bandit literatures. We analyze a broad class of two-stage pr…
Optimal variance-reduced stochastic approximation in Banach spaces
Wenlong Mou, Koulik Khamaru, Martin J. Wainwright +2
We study the problem of estimating the fixed point of a contractive operator defined on a separable Banach space. Focusing on a stochastic query model that provides noisy evaluatio…
Optimal and instance-dependent guarantees for Markovian linear stochastic approximation
Wenlong Mou, Ashwin Pananjady, Martin J. Wainwright +1
We study stochastic approximation procedures for approximately solving a -dimensional linear fixed point equation based on observing a trajectory of length from an ergodic M…
Optimal oracle inequalities for solving projected fixed-point equations
Wenlong Mou, Ashwin Pananjady, Martin J. Wainwright
Linear fixed point equations in Hilbert spaces arise in a variety of settings, including reinforcement learning, and computational methods for solving differential and integral equ…
On the Sample Complexity of Reinforcement Learning with Policy Space Generalization
Wenlong Mou, Zheng Wen, Xi Chen
We study the optimal sample complexity in large-scale Reinforcement Learning (RL) problems with policy space generalization, i.e. the agent has a prior knowledge that the optimal p…
ROOT-SGD: Sharp Nonasymptotics and Near-Optimal Asymptotics in a Single Algorithm
Chris Junchi Li, Wenlong Mou, Martin J. Wainwright +1
We study the problem of solving strongly convex and smooth unconstrained optimization problems using stochastic first-order algorithms. We devise a novel algorithm, referred to as…