papers

Publications (6)

cs.LG2025

Higher-Order Causal Message Passing for Experimentation with Complex Interference

Mohsen Bayati, Yuwei Luo, William Overman +2

Accurate estimation of treatment effects is essential for decision-making across various scientific fields. This task, however, becomes challenging in areas like social sciences an…

cs.LG2025

Can We Validate Counterfactual Estimations in the Presence of General Network Interference?

Sadegh Shirani, Yuwei Luo, William Overman +2

Randomized experiments have become a cornerstone of evidence-based decision-making in contexts ranging from online platforms to public health. However, in experimental settings wit…

cs.LG2021

Natural Actor-Critic Converges Globally for Hierarchical Linear Quadratic Regulator

Yuwei Luo, Zhuoran Yang, Zhaoran Wang +1

Multi-agent reinforcement learning has been successfully applied to a number of challenging problems. Despite these empirical successes, theoretical understanding of different algo…

stat.ML2020

Semiparametric Nonlinear Bipartite Graph Representation Learning with Provable Guarantees

Sen Na, Yuwei Luo, Zhuoran Yang +2

Graph representation learning is a ubiquitous task in machine learning where the goal is to embed each vertex into a low-dimensional vector space. We consider the bipartite graph a…

cs.LG2025

Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear Bandits

Yuwei Luo, Mohsen Bayati

This paper is motivated by recent research in the -dimensional stochastic linear bandit literature, which has revealed an unsettling discrepancy: algorithms like Thompson sampli…

cs.LG2022

Dynamic Regret Minimization for Control of Non-stationary Linear Dynamical Systems

Yuwei Luo, Varun Gupta, Mladen Kolar

We consider the problem of controlling a Linear Quadratic Regulator (LQR) system over a finite horizon with fixed and known cost matrices , but unknown and non-stationary…