8 papers
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)…
A Broader View of Thompson Sampling
Yanlin Qu, Hongseok Namkoong, Assaf Zeevi
Thompson Sampling is one of the most widely used and studied bandit algorithms, known for its simple structure, low regret performance, and solid theoretical guarantees. Yet, in st…
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…
AI paradigm for solving differential equations: first-principles data generation and scale-dilation operator AI solver
Xiangshu Gong, Zhiqiang Xie, Xiaowei Jin +4
Many problems are governed by differential equations (DEs). Artificial intelligence (AI) is a new path for solving DEs. However, data is very scarce and existing AI solvers struggl…
Deep Learning for Computing Convergence Rates of Markov Chains
Yanlin Qu, Jose Blanchet, Peter Glynn
Convergence rate analysis for general state-space Markov chains is fundamentally important in areas such as Markov chain Monte Carlo and algorithmic analysis (for computing explici…
Computable Bounds on Convergence of Markov Chains in Wasserstein Distance via Contractive Drift
Yanlin Qu, Jose Blanchet, Peter Glynn
We introduce a unified framework to estimate the convergence of Markov chains to equilibrium in Wasserstein distance. The framework can provide convergence bounds with rates rangin…