PulseAugur
EN
LIVE 21:28:20

New research advances contextual bandit algorithms for dynamic and complex environments

By PulseAugur Editorial · [9 sources] ·

Researchers are exploring advanced techniques for contextual bandit problems, focusing on improving regret bounds and handling dynamic environments. One paper introduces a retry-aware bandit algorithm that aims to optimize for the best outcome among multiple attempts, proving the first sublinear regret bound for this objective. Another study proposes active context selection to enhance simple regret in contextual bandits, showing significant improvements over passive sampling. Additionally, a new method called PONA is presented for offline contextual bandits that can effectively learn and select new actions by leveraging action features, outperforming existing methods that are limited to pre-defined action sets. Finally, a novel approach called RIE-Greedy uses regularization-induced exploration in contextual bandits, demonstrating theoretical equivalence to Thompson Sampling and practical effectiveness. AI

IMPACT These papers introduce novel algorithms and theoretical analyses for contextual bandit problems, potentially improving decision-making in recommendation systems and other applications.

RANK_REASON The cluster contains multiple academic papers on theoretical advancements in bandit algorithms.

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 9 sources. How we write summaries →

New research advances contextual bandit algorithms for dynamic and complex environments

COVERAGE [9]

  1. arXiv cs.LG TIER_1 English(EN) · Shuche Wang, Adarsh Barik, Vincent Y. F. Tan ·

    Bandit Convex Optimization with Gradient Prediction Adaptivity

    arXiv:2605.22191v1 Announce Type: new Abstract: Bandit convex optimization (BCO) is a fundamental online learning framework with partial feedback, where the learner observes only the loss incurred at the chosen decision point in each round. In this work, we investigate whether op…

  2. arXiv cs.LG TIER_1 English(EN) · Paavo Parmas ·

    Finite-Time Regret Analysis of Retry-Aware Bandits

    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@$k$. Given a posterior over arm values, ReMax chooses a sampling distribution that maximizes the posterior expected maximum rew…

  3. arXiv cs.LG TIER_1 English(EN) · Negar Kiyavash ·

    Active Context Selection Improves Simple Regret in Contextual Bandits

    We study the contextual multi-armed bandit problem with a finite context space (a.k.a. subpopulations), where the learner recommends a best action for each context and is evaluated by context-weighted simple regret. Our guarantees are worst-case over the reward distributions, whi…

  4. arXiv cs.LG TIER_1 English(EN) · Yuta Saito ·

    Offline Contextual Bandits in the Presence of New Actions

    Automated decision-making algorithms drive applications such as recommendation systems and search engines. These algorithms often rely on off-policy contextual bandits or off-policy learning (OPL). Conventionally, OPL selects actions that maximize the expected reward from an exis…

  5. arXiv stat.ML TIER_1 English(EN) · Avrim Blum, Marten Garicano, Kavya Ravichandran, Dravyansh Sharma ·

    Algorithm Design and Stronger Guarantees for the Improving Multi-Armed Bandits Problem

    arXiv:2511.10619v2 Announce Type: replace-cross Abstract: The improving multi-armed bandits problem is a formal model for allocating effort under uncertainty, motivated by scenarios such as investing research effort into new technologies, performing clinical trials, and hyperpara…

  6. arXiv stat.ML TIER_1 English(EN) · Hamed Khosravi, Xiaoming Huo ·

    Catching a Moving Subspace: Low-Rank Bandits Beyond Stationarity

    arXiv:2605.20269v1 Announce Type: cross Abstract: Many bandit deployments (recommendation, clinical dosing, ad targeting) share two facts prior work handles only in isolation: rewards live on a low-dimensional latent subspace, and that subspace drifts. Stationary low-rank bandits…

  7. arXiv stat.ML TIER_1 English(EN) · Sakshi Arya, Hyebin Song ·

    Batched Single-Index Global Multi-Armed Bandits with Covariates

    arXiv:2503.00565v3 Announce Type: replace Abstract: The multi-armed bandits (MAB) framework is a widely used approach for sequential decision-making, where a decision-maker selects an arm in each round with the goal of maximizing long-term rewards. In many practical applications,…

  8. arXiv stat.ML TIER_1 English(EN) · Tong Li, Thiago de Queiroz Casanova, Eric M. Schwartz, Victor Kostyuk, Dehan Kong, Joseph J. Williams ·

    RIE-Greedy: Regularization-Induced Exploration for Contextual Bandits

    arXiv:2603.11276v2 Announce Type: replace Abstract: Real-world contextual bandit problems with complex reward models are often tackled with iteratively trained models, such as boosting trees. However, it is difficult to directly apply simple and effective exploration strategies--…

  9. arXiv stat.ML TIER_1 English(EN) · Xiaoming Huo ·

    Catching a Moving Subspace: Low-Rank Bandits Beyond Stationarity

    Many bandit deployments (recommendation, clinical dosing, ad targeting) share two facts prior work handles only in isolation: rewards live on a low-dimensional latent subspace, and that subspace drifts. Stationary low-rank bandits exploit rank but break under subspace change; non…

RELATED ENTITIES

RELATED TOPICS