Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles

Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles

A fundamental challenge in contextual bandits is to develop flexible, general-purpose algorithms with computational requirements no worse than classical supervised learning tasks such as classification and regression. Algorithms based on regression have shown promising empirical success, but theoret...

Cur síos iomlán

Sonraí bibleagrafaíochta
Príomhchruthaitheoirí:	Foster, Dylan J, Rakhlin, Alexander
Rannpháirtithe:	Statistics and Data Science Center (Massachusetts Institute of Technology)
Formáid:	Alt
Teanga:	English
Foilsithe / Cruthaithe:	2021
Rochtain ar líne:	https://hdl.handle.net/1721.1/138306

Míreanna comhchosúla

Nonstationary Stochastic Bandits: UCB Policies and Minimax Regret
de réir: Lai Wei, et al.
Foilsithe / Cruthaithe: (2024-01-01)

Comparative Evaluation of Mean Cumulative Regret in Multi-Armed Bandit Algorithms: ETC, UCB, Asymptotically Optimal UCB, and TS
de réir: Lei Yicong
Foilsithe / Cruthaithe: (2025-01-01)

Top-k eXtreme Contextual Bandits with Arm Hierarchy
de réir: Sen, Rajat, et al.
Foilsithe / Cruthaithe: (2023)

Online and Distribution-Free Robustness: Regression and Contextual Bandits with Huber Contamination
de réir: Chen, Sitan, et al.
Foilsithe / Cruthaithe: (2022)

Contextual bandits with cross-learning
Foilsithe / Cruthaithe: (2021)

Contextual bandits with cross-learning
de réir: Balseiro, Santiago, et al.
Foilsithe / Cruthaithe: (2021)

Causal contextual bandits with one-shot data integration
de réir: Chandrasekar Subramanian, et al.
Foilsithe / Cruthaithe: (2024-12-01)

UCB Library to preserve ag literature
de réir: California Agriculture
Foilsithe / Cruthaithe: (1996-11-01)

UCB Library to preserve ag literature
Foilsithe / Cruthaithe: (1996-11-01)

Adaptive Noise Exploration for Neural Contextual Multi-Armed Bandits
de réir: Chi Wang, et al.
Foilsithe / Cruthaithe: (2025-01-01)

A Gaussian process approach for contextual bandit-based battery replacement
de réir: Zhou Tianshi
Foilsithe / Cruthaithe: (2025-01-01)

Contextual bandits to increase user prediction accuracy in movie recommendation system
de réir: Chen Yizhe
Foilsithe / Cruthaithe: (2025-01-01)

Review of Social Media Sentiment and Contextual Bandit Models in Stock Market Investment
de réir: Miao Ruicheng
Foilsithe / Cruthaithe: (2025-01-01)

Efficient Chlorophyll Prediction and Sampling in the Sea: A Real-Time Approach With UCB-Based Path Planning
de réir: Perihan Karakose, et al.
Foilsithe / Cruthaithe: (2025-01-01)

A Hybrid Proactive Caching System in Vehicular Networks Based on Contextual Multi-Armed Bandit Learning
de réir: Qiao Wang, et al.
Foilsithe / Cruthaithe: (2023-01-01)

Optimization as estimation with Gaussian processes in bandit settings
de réir: Wang, Zi, Ph.D. Massachusetts Institute of Technology
Foilsithe / Cruthaithe: (2016)

Undiscounted bandit games
de réir: Keller, G, et al.
Foilsithe / Cruthaithe: (2020)

Matching with semi-bandits
de réir: Kasy, M, et al.
Foilsithe / Cruthaithe: (2022)

Batched Bandit Problems
de réir: Perchet, Vianney, et al.
Foilsithe / Cruthaithe: (2015)

Linearly parameterized bandits
de réir: Tsitsiklis, John N., et al.
Foilsithe / Cruthaithe: (2012)

Copeland dueling bandits
de réir: Zoghi, M, et al.
Foilsithe / Cruthaithe: (2015)

Undiscounted bandit games
de réir: Keller, G, et al.
Foilsithe / Cruthaithe: (2019)

MSC-EVs and UCB-EVs promote skin wound healing and spatial transcriptome analysis
de réir: Ruonan Li, et al.
Foilsithe / Cruthaithe: (2025-02-01)

YOLOv8-UCB: Visual Detection of Pouch Battery Using Improved YOLOv8
de réir: Hao Hao, et al.
Foilsithe / Cruthaithe: (2024-01-01)

Just interpolate: Kernel “Ridgeless” regression can generalize
de réir: Liang, Tengyuan, et al.
Foilsithe / Cruthaithe: (2021)

Bandit Algorithms for Advertising Optimization: A Comparative Study
de réir: Tian Ziyue
Foilsithe / Cruthaithe: (2025-01-01)

Treatment of Radiation Bone Injury with Transplanted hUCB-MSCs via Wnt/β-Catenin
de réir: Yufeng Zhang, et al.
Foilsithe / Cruthaithe: (2021-01-01)

Strategic Experimentation with Exponential Bandits.
de réir: Keller, G, et al.
Foilsithe / Cruthaithe: (2005)

Strategic Experimentation with Exponential Bandits.
de réir: Cripps, M, et al.
Foilsithe / Cruthaithe: (2003)

Strategic experimentation with Poisson bandits.
de réir: Keller, G, et al.
Foilsithe / Cruthaithe: (2010)

Decentralized cooperative stochastic bandits
de réir: Martínez-Rubio, D, et al.
Foilsithe / Cruthaithe: (2019)

ON ERGODIC TWO-ARMED BANDITS
de réir: Tarres, P, et al.
Foilsithe / Cruthaithe: (2012)

Strategic experimentation with exponential bandits
de réir: Keller, G, et al.
Foilsithe / Cruthaithe: (2003)

Fair Probabilistic Multi-Armed Bandit With Applications to Network Optimization
de réir: Zhiwu Guo, et al.
Foilsithe / Cruthaithe: (2024-01-01)

Combining Multiple Strategies for Multiarmed Bandit Problems and Asymptotic Optimality
de réir: Hyeong Soo Chang, et al.
Foilsithe / Cruthaithe: (2015-01-01)

Oracle Essbase & Oracle OLAP : the guide to Oracle's multidimensional solution /
de réir: Schrader, Michael
Foilsithe / Cruthaithe: (2010)

Efficient crowdsourcing of unknown experts using bounded multi-armed bandits
de réir: Tran-Thanh, L, et al.
Foilsithe / Cruthaithe: (2014)

Behaviour and pupillometry in a bandit task
de réir: Moeller, M, et al.
Foilsithe / Cruthaithe: (2021)

Causally abstracted multi-armed bandits
de réir: Zennaro, FM, et al.
Foilsithe / Cruthaithe: (2024)

Aging Wireless Bandits: Regret Analysis and Order-Optimal Learning Algorithm
de réir: Atay, Eray Unsal, et al.
Foilsithe / Cruthaithe: (2022)