Combinatorial Pure Exploration of Multi-Armed Bandits

Authors: Shouyuan Chen, Tian Lin, Irwin King, Michael R Lyu, Wei Chen

NeurIPS 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We study the combinatorial pure exploration (CPE) problem in the stochastic multi-armed bandit setting... We present general learning algorithms... We prove problem-dependent upper bounds of our algorithms. Our analysis exploits the combinatorial structures... We also establish a general problem-dependent lower bound for the CPE problem.
Researcher Affiliation Collaboration 1The Chinese University of Hong Kong 2Tsinghua University 3Microsoft Research Asia
Pseudocode Yes Algorithm 1 CLUCB: Combinatorial Lower-Upper Confidence Bound; Algorithm 2 CSAR: Combinatorial Successive Accept Reject
Open Source Code No The paper does not provide any links to open-source code or explicitly state that code for the described methodology is available.
Open Datasets No This is a theoretical paper that focuses on algorithm design and analysis, and it does not use or refer to any datasets for training or evaluation.
Dataset Splits No This is a theoretical paper that does not involve datasets or data splitting, thus no training, validation, or test splits are mentioned.
Hardware Specification No The paper is theoretical and does not describe empirical experiments. Therefore, no hardware specifications are mentioned for running experiments.
Software Dependencies No The paper is theoretical and does not describe empirical experiments requiring specific software dependencies or versions. It refers to conceptual 'oracles' rather than actual software.
Experiment Setup No The paper is theoretical and describes algorithms and their bounds, but it does not include details on an experimental setup, hyperparameters, or training configurations.