会员服务
Robust and Computationally Efficient Linear Contextual Bandits under Adversarial Corruption and Heavy-Tailed Noise
Robust and Computationally Efficient Linear Contextual Bandits under Adversarial Corruption and Heavy-Tailed Noise
Arxiv
0+阅读 · 3月16日
Sampling as Bandits: Evaluation-Efficient Design for Black-Box Densities
Arxiv
0+阅读 · 3月14日
Batched Kernelized Bandits: Refinements and Extensions
Arxiv
0+阅读 · 3月13日
What Do We Care About in Bandits with Noncompliance? BRACE: Bandits with Recommendations, Abstention, and Certified Effects
Arxiv
0+阅读 · 3月10日
Communication-Corruption Coupling and Verification in Cooperative Multi-Objective Bandits
Arxiv
0+阅读 · 2月20日
Revisiting Matrix Sketching in Linear Bandits: Achieving Sublinear Regret via Dyadic Block Sketching
Arxiv
0+阅读 · 2月27日
Inverse Contextual Bandits without Rewards: Learning from a Non-Stationary Learner via Suffix Imitation
Arxiv
0+阅读 · 3月4日
Adaptive Prior Selection in Gaussian Process Bandits with Thompson Sampling
Arxiv
0+阅读 · 3月12日
Combinatorial Allocation Bandits with Nonlinear Arm Utility
Arxiv
0+阅读 · 3月7日
Buzz, Choose, Forget: A Meta-Bandit Framework for Bee-Like Decision Making
Arxiv
0+阅读 · 3月4日
Choosing the Better Bandit Algorithm under Data Sharing: When Do A/B Experiments Work?
Arxiv
0+阅读 · 2月23日
Invariance-Based Dynamic Regret Minimization
Arxiv
0+阅读 · 3月4日
Sustainable Multi-Agent Crowdsourcing via Physics-Informed Bandits
Arxiv
0+阅读 · 2月25日
Probe-then-Commit Multi-Objective Bandits: Theoretical Benefits of Limited Multi-Arm Feedback
Arxiv
0+阅读 · 2月20日
Rigidity in LLM Bandits with Implications for Human-AI Dyads
Arxiv
0+阅读 · 3月8日
参考链接
微信扫码咨询专知VIP会员
Top