collaborators

9 papers

math.PR2026

A Harris recurrent continuous-time Markov process without wide-sense regenerative structure

Yanlin Qu, Peter Glynn

While Harris recurrent Markov chains (in discrete time) automatically exhibit wide-sense regenerative structure, we construct a Harris recurrent Markov process (in continuous time)…

math.OC2026

Fast Convergence of Policy Regret in Learning Stochastic Optimal Control

Shengbo Wang, Jose Blanchet, Peter Glynn

Policy learning in modern operations environments faces a fundamental tension between limited operational data and the large, often continuous, state and action spaces over which g…

stat.ML2026

Statistical Inference for Stochastic Gradient Descent: Beyond Finite Variance

Jose Blanchet, Peter Glynn, Wenhao Yang

Stochastic gradient descent (SGD) is foundational to large-scale statistical learning and stochastic optimization. However, in some modern statistical learning problems, stochastic…

math.ST2026

Statistical Inference in Causal Partial Identification with Smooth Densities

Sirui Lin, Zijun Gao, Jose Blanchet +1

Many causal quantities are only partially identifiable due to the inherent missingness of potential outcomes, and the associated partial identification (PI) sets can be obtained by…

stat.ME2026

Causal Partial Identification via Conditional Optimal Transport

Sirui Lin, Zijun Gao, Jose Blanchet +1

We study the estimation of causal estimand involving the joint distribution of treatment and control outcomes for a single unit. In typical causal inference settings, it is impossi…

cs.LG2025

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

Yanlin Qu, Jose Blanchet, Peter Glynn

Lyapunov functions are fundamental to establishing the stability of Markovian models, yet their construction typically demands substantial creativity and analytical effort. In this…