TS-Insight: Visualizing Thompson Sampling for Verification and XAI
This addresses the need for interpretable decision-making in sensitive domains, though it is incremental as it builds on existing Thompson Sampling methods.
The paper tackles the problem of Thompson Sampling algorithms being black boxes that hinder debugging and trust, by introducing TS-Insight, a visual analytics tool that traces posteriors, evidence counts, and sampling outcomes to enable verification, diagnosis, and explainability.
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.