arXiv Machine Learning June 4, 2026 By Foo Hui-Mean, Yuan-chin I Chang

ALMAB-DC: Active Learning, Multi-Armed Bandits, and Distributed Computing for Sequential Experimental Design and Black-Box Optimization

Read the original on arXiv Machine Learning →

arXiv:2603. 21180v4 Announce Type: replace Abstract: Sequential experimental design under expensive, gradient-free objectives is a central challenge in computational statistics: evaluation budgets are tightly constrained and information must be extracted efficiently from each observation.

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

arXiv Machine Learning

Jun 29

Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Bandits

arXiv:2602. 09456v2 Announce Type: replace Abstract: We propose an algorithmic framework, Offline Estimation to Decisions (OE2D), that efficiently reduces contextual bandit learning with general reward function approximation to offline regression.

By Hao Qin, Chicheng Zhang

reinforcement-learning

arXiv Machine Learning

Jul 13

Optimal Top-$k$ Identification from Pairwise Comparisons

arXiv:2607. 08979v1 Announce Type: new Abstract: We study the active learning problem of fixed-confidence top-$k$ identification from noisy pairwise comparisons.

By Motti Goldberger, Nils Rudi

reinforcement-learning

arXiv Machine Learning

Jun 16

Fast Non-Episodic Finite-Horizon RL with K-Step Lookahead Thresholding

arXiv:2602. 00781v2 Announce Type: replace Abstract: Online reinforcement learning in non-episodic, finite-horizon MDPs remains underexplored and is challenged by the need to estimate returns to a fixed terminal time.

By Jiamin Xu, Kyra Gan

reinforcement-learning benchmarks

arXiv Machine Learning

Aug 4

Meritocratic Fairness via $K$-Shapley Values in Budgeted Combinatorial Bandits with Full-Bandit Feedback

arXiv:2605. 00762v2 Announce Type: replace Abstract: We study meritocratic fairness in budgeted combinatorial multi-armed bandits with full-bandit feedback, where a learner selects at most $K$ arms per time step and observes only the noisy aggregate reward of the selected set.

By Shradha Sharma, Shweta Jain, Swapnil Dhamal

reinforcement-learning safety

arXiv Machine Learning

Jul 8

No-Regret Gaussian Process Optimization of Time-Varying Functions

arXiv:2512. 00517v3 Announce Type: replace-cross Abstract: Sequential optimization of black-box functions from noisy evaluations has been widely studied, with Gaussian Process bandit algorithms such as GP-UCB guaranteeing no-regret in stationary settings.

By Eliabelle Mauduit, Elo\"ise Berthier, Andrea Simonetto

reinforcement-learning

arXiv Machine Learning

Jun 2

Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback

arXiv:2606. 01081v1 Announce Type: new Abstract: Decision-focused learning (DFL) trains predictive models by optimizing downstream decision quality rather than standalone prediction accuracy.

By Wyame Benslimane, Tinghan Ye, Pascal Van Hentenryck, Paul Grigas

reinforcement-learning benchmarks

Related stories

Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Bandits

Optimal Top-$k$ Identification from Pairwise Comparisons

Fast Non-Episodic Finite-Horizon RL with K-Step Lookahead Thresholding

Meritocratic Fairness via $K$-Shapley Values in Budgeted Combinatorial Bandits with Full-Bandit Feedback

No-Regret Gaussian Process Optimization of Time-Varying Functions

Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback