TS-Insight: Visualizing Thompson Sampling for Verification and XAI

TL;DR

TS-Insight is a visual analytics tool that makes Thompson Sampling algorithms more transparent, aiding debugging, verification, and trust in complex decision-making scenarios.

Contribution

It introduces a novel visualization tool that elucidates the internal workings of Thompson Sampling algorithms for model developers.

Findings

Enables verification of exploration/exploitation dynamics.

Facilitates debugging of Thompson Sampling algorithms.

Improves interpretability in sensitive domains.

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.