Instance-Sensitive Algorithms for Pure Exploration in Multinomial Logit Bandit

Authors: Nikolai Karpov, Qin Zhang7096-7103

AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we give efficient algorithms for pure exploration in MNL-bandit. Our algorithms achieve instancesensitive pull complexities. We also complement the upper bounds by an almost matching lower bound.
Researcher Affiliation Academia Indiana University Bloomington Luddy Hall, RM 3044 700 North Woodlawn Avenue Bloomington, IN 47408-3901, USA nkarpov@iu.edu, qzhangcs@indiana.edu
Pseudocode Yes Algorithm 1: EXPLORE(i) ... Algorithm 2: PRUNE(I, K, a, b) ... Algorithm 3: The Fixed Confidence Algorithm for MNL-Bandit ... Algorithm 4: EXPLORESET(S) ... Algorithm 5: Improved Fixed Confidence Algorithm for MNL-bandit
Open Source Code No The paper does not provide any statement or link indicating that source code for the described methodology is publicly available.
Open Datasets No The paper is theoretical and does not conduct experiments on a dataset, thus it does not mention a training dataset.
Dataset Splits No The paper is theoretical and does not conduct experiments on a dataset, thus it does not mention training, validation, or test splits.
Hardware Specification No The paper is theoretical and focuses on algorithms and complexity, without discussing the hardware used for any computational tasks.
Software Dependencies No The paper is theoretical and describes algorithms, but it does not mention any specific software dependencies or version numbers.
Experiment Setup No The paper describes theoretical algorithms and their complexities but does not detail an experimental setup, as no empirical experiments are reported.