Salvato in:
Dettagli Bibliografici
Autori principali: Vares, Parsa, Durant, Éloi, Pang, Jun, Médoc, Nicolas, Ghoniem, Mohammad
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2507.19898
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915453830430720
author Vares, Parsa
Durant, Éloi
Pang, Jun
Médoc, Nicolas
Ghoniem, Mohammad
author_facet Vares, Parsa
Durant, Éloi
Pang, Jun
Médoc, Nicolas
Ghoniem, Mohammad
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_19898
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TS-Insight: Visualizing Thompson Sampling for Verification and XAI
Vares, Parsa
Durant, Éloi
Pang, Jun
Médoc, Nicolas
Ghoniem, Mohammad
Human-Computer Interaction
Artificial Intelligence
Machine Learning
I.2.6; H.5.2
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.
title TS-Insight: Visualizing Thompson Sampling for Verification and XAI
topic Human-Computer Interaction
Artificial Intelligence
Machine Learning
I.2.6; H.5.2
url https://arxiv.org/abs/2507.19898