Lin Xiao

RESEARCH SCIENTIST | SEATTLE, UNITED STATES

Lin Xiao is a Research Scientist at Meta AI Research in Seattle, Washington. He received his PhD from Stanford University and was a postdoctoral fellow at California Institute of Technology. Before joining Meta, he spent 14 years as a Researcher at Microsoft Research. His current research interests include optimization algorithms and theory, machine learning, reinforcement learning, and parallel and distributed computing.

Lin's Publications

August 16, 2024

THEORY

REINFORCEMENT LEARNING

Dual Approximation Policy Optimization

Zhihan Xiong, Maryam Fazel, Lin Xiao

August 16, 2024

July 08, 2024

THEORY

CORE MACHINE LEARNING

An Adaptive Stochastic Gradient Method with Non-negative Gauss-Newton Stepsizes

Antonio Orvieto, Lin Xiao

July 08, 2024

September 01, 2022

On the Convergence Rates of Policy Gradient Methods

Lin Xiao

September 01, 2022

July 13, 2022

Federated Learning with Partial Model Personalization

Lin Xiao, Abdelrahman Mohamed, Kshitiz Malik, Maziar Sanjabi, Mike Rabbat, Krishna Pilllutla

July 13, 2022

October 21, 2021

Stochastic Variance-Reduced Prox-Linear Algorithms for Nonconvex Stochastic Optimization

Lin Xiao, Junyu Zhang

October 21, 2021