TS-Insight: Visualizing Thompson Sampling for Verification and XAI

2025/07/26 by Vares, Parsa, Durant, Éloi, Pang, Jun +2
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #H.5.2 #Human-Computer Interaction (cs.HC) #I.2.6 #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.2507.19898

Abstract

Thompson Sampling (TS) and its variants are powerful Multi-Armed Bandit algorithms used to balance exploration and exploitation strategies in active learning. Yet, their probabilistic nature often turns them into a "black box", hindering debugging and trust. We introduce TS-Insight, a visual analytics tool explicitly designed to shed light on the internal decision mechanisms of Thompson Sampling-based algorithms, for model developers. It comprises multiple plots, tracing for each arm the evolving posteriors, evidence counts, and sampling outcomes, enabling the verification, diagnosis, and explainability of exploration/exploitation dynamics. This tool aims at fostering trust and facilitating effective debugging and deployment in complex binary decision-making scenarios especially in sensitive domains requiring interpretable decision-making.

Citations

• Algorithm Selection for Deep Active Learning with Imbalanced Datasets
• Taming Non-stationary Bandits: A Bayesian Approach
• Computing and Graphing Highest Density Regions

Related

• Bootstrapped Thompson Sampling and Deep Exploration
• Thompson Sampling with Virtual Helping Agents
• TS-UCB: Improving on Thompson Sampling With Little to No Additional Computation
• Contextual Thompson Sampling via Generation of Missing Data
• Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown