arXiv Machine Learning
Regret Analysis of Retry-Based Bandits
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jun 2
Finite-Time Regret Analysis of Retry-Aware Bandits
arXiv:2605. 20854v2 Announce Type: replace Abstract: We study a stochastic bandit algorithm motivated by retry-aware objectives that value the best outcome among multiple attempts, such as pass@$k$ and max@$k$.
arXiv AI
2d ago
Bandits with Multiple Optimal Arms: Minimax Regret and Non-Adaptivit
arXiv:2609. 38659v1 Announce Type: cross Abstract: We study multi-armed bandits (MAB) with multiple optimal arms, motivated by the fact that many practical decision making problems admit multiple correct answers.
arXiv AI
1d ago
Bandits with Multiple Optimal Arms: Minimax Regret and Non-Adaptivity
arXiv:2609.38659v2 Announce Type: replace-cross Abstract: We study multi-armed bandits (MAB) with multiple optimal arms, motivated by the fact that many practical decision making problems admit multi...
arXiv Machine Learning
Sep 22
Multi-Armed Bernoulli Bandits via Minimax Single-Arm Stopping
arXiv:2609. 22690v1 Announce Type: new Abstract: We develop an index policy for finite-horizon Bernoulli multi-armed bandits from minimax solutions to single-arm bandit (SAB) problems.
arXiv Machine Learning
Sep 25
Exact Bayes Regret and Asymptotic Optimality in High-Dimensional Gaussian Bandits
The paper analyzes Bayesian linear bandits with isotropic Gaussian parameters, independent Gaussian arms, and Gaussian reward noise when the time horizon scales with the dimension. It derives explicit limits for the normalized posterior uncertainty and parameter overlaps, yielding exact regret curves for several policies—including Thompson sampling, posterior‑mean greedy selection, and scaled‑covariance variants. The results show that posterior‑mean greedy selection achieves the optimal Bayes regret, while Thompson sampling incurs a strictly larger leading regret whose ratio to greedy lies between one and two, approaching two for long horizons.
arXiv Machine Learning
Jul 7
Replicability is Asymptotically Free in Multi-armed Bandits
arXiv:2402. 07391v3 Announce Type: replace-cross Abstract: We consider a replicable stochastic multi-armed bandit algorithm that ensures, with high probability, that the algorithm's sequence of actions is not affected by the randomness inherent in the dataset.