Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Exploiting Correlated Auxiliary Feedback in Parameterized Bandits
Authors: Arun Verma, Zhongxiang Dai, YAO SHU, Bryan Kian Hsiang Low
NeurIPS 2023 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | To validate our theoretical results, we empirically demonstrate the performance gain due to auxiliary feedback in different settings of parameterized bandits. We repeat all our experiments 50 times and show the regret as defined in Eq. (1) with a 95% confidence interval. |
| Researcher Affiliation | Academia | Arun Verma Zhongxiang Dai Yao Shu Bryan Kian Hsiang Low Department of Computer Science, National University of Singapore, Republic of Singapore EMAIL |
| Pseudocode | Yes | OFUL-AF Algorithm for Linear Bandits with Auxiliary Feedback |
| Open Source Code | No | The paper does not contain any explicit statements about open-source code availability, repository links, or code in supplementary materials. |
| Open Datasets | No | The paper describes synthetic datasets generated by the authors (e.g., "We first generate a 2-dimensional synthetic dataset with 5000 data samples"), but does not provide concrete access information (link, DOI, repository, or formal citation) for them to be publicly available. |
| Dataset Splits | No | The paper mentions generating data samples (e.g., "5000 data samples") but does not provide specific details on training, validation, or test splits (percentages, absolute counts, or references to predefined splits). |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details, such as library or solver names with version numbers, needed to replicate the experiment. |
| Experiment Setup | Yes | In all linear bandits experiments, we use λ = 0.01, L = 2.236, S = 1, and δ = 0.05. ... The default value of σ2 v = 0.01 and σ2 w = 0.01. |