task · first seen 4 Oct 2026
multi-armed bandit
Also: MAB, MMAB, bandits, bandit problem, bandit feedback, bandit algorithm, stochastic bandits
A sequential decision problem where an agent repeatedly chooses among arms with unknown rewards to maximize cumulative reward.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Billion-Scale Thumbnail Optimization for Uncurated Short-Form Videos via Multi-Armed BanditsPapers · 4 Oct 2026 · Ying Han, Ling Liu, Fabio Soldo, Vu Nguyen, Danio Wang, Liz Kidd, Yongle Cao, Th…
- FlexiFlow: Bandit-based Model Switching in ML WorkflowsPapers · 5 Oct 2026 · Abhilash Jindal, Todd Nief, Bhanu Prakash Vangala, Shankaradithyaa V, Tvisha Mal…
- Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability RegretPapers · 6 Oct 2026 · Avishek Ghosh
- Expected Sample Complexity in Multi-Armed BanditsPapers · 7 Oct 2026 · Nadav Sukenik, Nadav Merlis
- Beyond Reward Suppression: Near-Optimal Offline Attacks on Warm-Start Bandits with Bounded RewardsPapers · 7 Oct 2026 · Qirun Zeng, Manhin Poon, Xiangxiang Dai, Qixin Zhang, Jinhang Zuo
- Reliable Scale-Free Bandits via Empirical LikelihoodPapers · 13 Oct 2026 · Pratham Gupta, Alhad Sethi, Shubhada Agrawal
Latest sources
- Generalized Prediction Set with Bandit FeedbackPapers · 16 Nov 2026 · Zhou Wang, Xingye Qiao
- Adversarially Batched Online LearningPapers · 12 Nov 2026 · Mingda Qiao, Kerui Wu
- Ballad: Bandit-Based LLM Routing for Automated Heuristic DiscoveryPapers · 12 Nov 2026 · Samidha Verma, Ankit Anand, Sayan Ranu
- UCB-min: Combining Bandits Under Variance Heterogeneity (Extended Version)Papers · 9 Nov 2026 · Lilia Izri, Benoit Groz, Silviu Maniu
- Visible Tails: Characterizing Adaptation to Unknown Moments in Heavy-Tailed BanditsPapers · 9 Nov 2026 · Tuan Ngoc Do, Hai Duc Nguyen
- Efficient Online Submodular Maximization with Bandit FeedbackPapers · 9 Nov 2026 · Iasonas Nikolaou, Evimaria Terzi
- Regret without Optimal-Arm Feedback under Reward-Dependent DelaysPapers · 8 Nov 2026 · Zhong Han
- NCCL-BOT: Closing the Loop on NCCL's Cost Model with Online BanditsPapers · 8 Nov 2026 · Hanan Shteingart, Amedeo Sapio, Chen Avin, Devendar Bureddy, Manjunath Gorentla…
- Instance-dependent sequential limits as an exact information ledgerPapers · 30 Oct 2026 · Akshay Balsubramani
- Adaptive search with path-constrained mobile sensors using multi-arm banditsPapers · 29 Oct 2026 · Abraham P. Vinod, Parth K. Thaker, Gautam Dasarathy, Stefano Di Cairano
- RiskyPy: Toward Model-Calibrated Prompt Generation for Joint Security and Functionality Evaluation of LLM-Generated CodePapers · 29 Oct 2026 · Zacharie Chenail-Larcher, Daniele Lunghi, Melissa Tessa, Quentin Stiévenart, Ja…
- Achieving Minimax-Optimal First-Order and Best-of-Both-Worlds Regret Simultaneously in Multi-Armed BanditsPapers · 29 Oct 2026 · Mengxiao Zhang