A Broader View of Thompson Sampling

with Hongseok Namkoong and Assaf Zeevi

- Coming soon
- A preliminary version is under review at NeurIPS 2025

Deep Learning for Markov Chains: Lyapunov Functions, Poisson's Equation, and Stationary Distributions

with Jose Blanchet and Peter Glynn

- Submitted to Queueing Systems, arXiv
- Special Issue: 40 Years of QUESTA

Deep Learning for Computing Convergence Rates of Markov Chains

with Jose Blanchet and Peter Glynn, NeurIPS 2024 (spotlight), arXiv

Computable Bounds on Convergence of Markov Chains in Wasserstein Distance via Contractive Drift

with Jose Blanchet and Peter Glynn, Annals of Applied Probability, arXiv, 2025

- Applied Probability Society Best Student Paper Prize, 2023
- Applied Probability Society Conference Best Poster Award, 2023

Markov Chain Convergence Analysis:
From Pen and Paper to Deep Learning

PhD thesis, Stanford University

Rubik's Cube Scrambling Requires at Least 26 Random Moves

with Tomas Rokicki and Hillary Yang, arXiv, slides

Double Distributionally Robust Bid Shading for First Price Auctions

with Ravi Kant, Yan Chen, Brendan Kitts, San Gultekin, Aaron Flores, Jose Blanchet, arXiv, slides

On a New Characterization of Harris Recurrence for Markov Chains and Processes

with Peter Glynn, Mathematics, 2023

Strong Limit Interchange Property of a Sequence of Markov Processes

with Jose Blanchet and Peter Glynn, preprint

Estimating the Convergence Rate to Equilibrium of a Markov Chain via Simulation

with Jose Blanchet and Peter Glynn, preprint

Bias of Markov Chain Sample Quantile

with Peter Glynn, preprint

Uniform Edgeworth Expansion for Markov Chains

with Peter Glynn, preprint