arXiv Machine Learning June 5, 2026 By David Janz, Shuai Liu, Alex Ayoub, Csaba Szepesv\'ari

Exploration via linearly perturbed loss minimisation

Read the original on arXiv Machine Learning →

arXiv:2311. 07565v3 Announce Type: replace Abstract: We introduce exploration via linear loss perturbations (EVILL), a randomised exploration method for structured stochastic bandit problems that works by solving for the minimiser of a linearly perturbed regularised negative log-likelihood function.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

reinforcement-learning

arXiv Machine Learning

Jun 19

Adversarial Bandit Optimization with Globally Bounded Perturbations to Convex Losses

arXiv:2606. 19891v1 Announce Type: new Abstract: We study adversarial bandit optimization in which the loss functions may be non-convex and non-smooth.

By Zhuoyu Cheng, Kohei Hatano, Eiji Takimoto

reinforcement-learning safety

arXiv Machine Learning

Jun 4

When and why randomised exploration works (in linear bandits)

arXiv:2502. 08870v2 Announce Type: replace Abstract: We provide an approach for the analysis of randomised exploration algorithms like Thompson sampling that does not rely on forced optimism or posterior inflation.

By Marc Abeille, David Janz, Ciara Pike-Burke

reinforcement-learning

arXiv Machine Learning

Jun 30

Randomized Exploration for Linear Bandits via Absolute Perturbations

arXiv:2606. 28616v1 Announce Type: new Abstract: In stochastic linear bandits, the canonical Upper Confidence Bound (UCB) algorithm admits a simple frequentist regret analysis but can be computationally demanding, while Thompson Sampling (TS) is computationally attractive yet typically harder to analyze due to its non-optimistic nature.

By Toshinori Kitamura, Shuai Liu, Csaba Szepesv\'ari

arXiv Machine Learning

Aug 4

A Perturbation Approach to Unconstrained Linear Bandits

arXiv:2603. 28201v3 Announce Type: replace Abstract: We revisit the standard perturbation-based approach of Abernethy et al.

By Andrew Jacobsen, Dorian Baudry, Shinji Ito, Nicol\`o Cesa-Bianchi

reinforcement-learning safety

arXiv Machine Learning

Jun 29

Self-Concordant Perturbations for Linear Bandits

arXiv:2510. 24187v3 Announce Type: replace-cross Abstract: We consider the adversarial linear bandits setting and present a unified algorithmic framework that bridges Follow-the-Regularized-Leader (FTRL) and Follow-the-Perturbed-Leader (FTPL) methods, extending the known connection between them from the full-information setting.

By Lucas L\'evy, Jean-Lou Valeau, Arya Akhavan, Patrick Rebeschini

safety

arXiv AI

Jun 16

Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts

arXiv:2606. 14929v1 Announce Type: cross Abstract: Modern recommendation systems increasingly rely on dynamically routing diverse queries to multiple embedding models.

By Yan Dai, Negin Golrezaei, Patrick Jaillet

rag reinforcement-learning safety

Related stories

Adversarial Bandit Optimization with Globally Bounded Perturbations to Convex Losses

When and why randomised exploration works (in linear bandits)

Randomized Exploration for Linear Bandits via Absolute Perturbations

A Perturbation Approach to Unconstrained Linear Bandits

Self-Concordant Perturbations for Linear Bandits

Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts