Picture for Peter W. Glynn

Peter W. Glynn

Online Linear Programming with Batching

Add code
Aug 01, 2024
Viaarxiv icon

Overlapping Batch Confidence Intervals on Statistical Functionals Constructed from Time Series: Application to Quantiles, Optimization, and Estimation

Add code
Jul 17, 2023
Viaarxiv icon

Minimax Optimal Estimation of Stability Under Distribution Shift

Add code
Dec 13, 2022
Viaarxiv icon

Risk-Sensitive Markov Decision Processes with Long-Run CVaR Criterion

Add code
Oct 17, 2022
Figure 1 for Risk-Sensitive Markov Decision Processes with Long-Run CVaR Criterion
Figure 2 for Risk-Sensitive Markov Decision Processes with Long-Run CVaR Criterion
Figure 3 for Risk-Sensitive Markov Decision Processes with Long-Run CVaR Criterion
Figure 4 for Risk-Sensitive Markov Decision Processes with Long-Run CVaR Criterion
Viaarxiv icon

The Typical Behavior of Bandit Algorithms

Add code
Oct 11, 2022
Figure 1 for The Typical Behavior of Bandit Algorithms
Figure 2 for The Typical Behavior of Bandit Algorithms
Figure 3 for The Typical Behavior of Bandit Algorithms
Viaarxiv icon

The Fragility of Optimized Bandit Algorithms

Add code
Sep 28, 2021
Figure 1 for The Fragility of Optimized Bandit Algorithms
Figure 2 for The Fragility of Optimized Bandit Algorithms
Viaarxiv icon

Distributed stochastic optimization with large delays

Add code
Jul 06, 2021
Figure 1 for Distributed stochastic optimization with large delays
Figure 2 for Distributed stochastic optimization with large delays
Viaarxiv icon

Diffusion Approximations for Thompson Sampling

Add code
May 19, 2021
Viaarxiv icon

On Incorporating Forecasts into Linear State Space Model Markov Decision Processes

Add code
Mar 12, 2021
Figure 1 for On Incorporating Forecasts into Linear State Space Model Markov Decision Processes
Figure 2 for On Incorporating Forecasts into Linear State Space Model Markov Decision Processes
Figure 3 for On Incorporating Forecasts into Linear State Space Model Markov Decision Processes
Figure 4 for On Incorporating Forecasts into Linear State Space Model Markov Decision Processes
Viaarxiv icon

Sequential Batch Learning in Finite-Action Linear Contextual Bandits

Add code
Apr 14, 2020
Viaarxiv icon