22 citations · 73 across the 12 of their papers we have counts for
12 papers
Fast PAC Global Optimization via Restarted Langevin: Exploration, Exploitation, and Degenerate Cooling
Ioannis Kontoyiannis, Sean Meyn
This paper addresses a fundamental question in non-convex optimization: \textit{How should a stochastic optimizer allocate computation between global exploration and local exploita…
Markovian Foundations for Quasi-Stochastic Approximation with Applications to Extremum Seeking Control
Caio Kalil Lauand, Sean Meyn
This paper concerns quasi-stochastic approximation (QSA) to solve root finding problems commonly found in applications to optimization and reinforcement learning. The general const…
The ODE Method for Asymptotic Statistics in Stochastic Approximation and Reinforcement Learning
Vivek Borkar, Shuhang Chen, Adithya Devraj +2
The paper concerns the -dimensional stochastic approximation recursion, where is a stochastic process on a general st…
Q-learning with Uniformly Bounded Variance: Large Discounting is Not a Barrier to Fast Learning
Adithya M. Devraj, Sean P. Meyn
Sample complexity bounds are a common performance metric in the Reinforcement Learning literature. In the discounted cost, infinite horizon setting, all of the known bounds have a…
On the -Norm Ergodicity of Markov Processes in Continuous Time
I. Kontoyiannis, S. P. Meyn
Consider a Markov process evolving on a Polish space . A version of the -Norm Ergodic Theorem is obtained: Suppose that the process is -irreduci…
Geometric Ergodicity and the Spectral Gap of Non-Reversible Markov Chains
Ioannis Kontoyiannis, Sean P. Meyn
We argue that the spectral theory of non-reversible Markov chains may often be more effectively cast within the framework of the naturally associated weighted- space $L_\…