arXiv Statistics ML
Balanced Sampling in Stochastic Multi-objective Bandits
Read the original on arXiv Statistics ML →The Flow has not summarised this story yet — read it at arXiv Statistics ML.
Related stories
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.
arXiv Statistics ML
Oct 2
Sharp Non-Asymptotic Analysis of the Penalized Challenger in $\beta$-EB-TCI for Bernoulli Bandits
arXiv:2610.01951v1 Announce Type: cross Abstract: Top-two algorithms are simple and effective for fixed-confidence best-arm identification, but their sharp non-asymptotic behavior is still not well u...
arXiv Machine Learning
Jun 16
Multi-User Dueling Bandits: A Fair Approach using Nash Social Welfare
arXiv:2605. 01961v2 Announce Type: replace Abstract: Learning from human preference data is becoming a useful tool, from fine-tuning large language models to training reinforcement learning agents.
arXiv Machine Learning
Oct 2
Regret Analysis of Retry-Based Bandits
arXiv:2605.20854v3 Announce Type: replace Abstract: We provide the first regret analysis of ReMax in stochastic multi-armed bandits. Originally introduced for reinforcement learning, ReMax is motivat...
arXiv Machine Learning
Oct 16
Transfer Learning in Bandits from Unknown Adaptive Policies: Problem-Dependent Lower and Upper Bounds
The paper investigates transfer learning in stochastic multi‑armed bandits when historical data come from an unknown adaptive policy. It establishes asymptotic problem‑dependent lower bounds and introduces the KL‑UCB‑Transfer algorithm, which combines online and historical data to achieve logarithmic regret with an improved constant under certain mean‑gap conditions. The study also relaxes the source‑target discrepancy assumption to a one‑sided condition, demonstrating that logarithmic regret can still be achieved under misspecification and identifying regimes of improvement, degradation, or loss of guarantee.
arXiv Machine Learning
Oct 7
Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret
arXiv:2610.07737v1 Announce Type: cross Abstract: We study fair multi-armed bandits under the Nash Social Welfare (NSW) objective, which measures performance via the geometric mean of accumulated rew...