Incentivizing Exploration with Linear Contexts and Combinatorial Actions

Authors: Mark Sellke

ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We give an analog of this result for linear bandits, where the independence of the prior is replaced by a natural convexity condition. This opens up the possibility of efficient and regret-optimal incentivized exploration in high-dimensional action spaces. In the semibandit model, we also improve the sample complexity for the pre-Thompson sampling phase of initial data collection. and sections like 3. Linear Bandit and 4. Initial Exploration for Combinatorial Semibandit are filled with lemmas, theorems, and proofs, without any mention of empirical evaluation, datasets, or performance metrics from experiments.
Researcher Affiliation Industry 1Amazon Core AI. Correspondence to: Mark Sellke <msellke@gmail.com>.
Pseudocode Yes Algorithm 1: Semibandit BIC Exploration
Open Source Code No The paper does not contain any statements about releasing code, nor does it provide a link to a code repository.
Open Datasets No The paper discusses bandit models (linear bandit, combinatorial semibandit) conceptually but does not refer to any specific public datasets by name or provide links/citations for data used in experiments. It's a theoretical paper.
Dataset Splits No The paper is theoretical and does not involve empirical evaluation with data splits. There is no mention of train/validation/test splits.
Hardware Specification No The paper is theoretical and does not describe any experimental setup or the hardware used to run experiments.
Software Dependencies No The paper is theoretical and does not describe any specific software dependencies with version numbers for implementation or experimentation.
Experiment Setup No The paper is theoretical and focuses on mathematical proofs and algorithm design. It does not provide details on experimental setup, hyperparameters, or training configurations.