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].
Pure Exploration in Kernel and Neural Bandits
Authors: Yinglun Zhu, Dongruo Zhou, Ruoxi Jiang, Quanquan Gu, Rebecca Willett, Robert Nowak
NeurIPS 2021 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments conducted on both synthetic and real-world datasets demonstrate the efficacy of our methods. |
| Researcher Affiliation | Academia | Yinglun Zhu Department of Computer Sciences University of Wisconsin-Madison Madison, WI 53706 EMAIL; Dongruo Zhou Department of Computer Science University of California, Los Angeles Los Angeles, CA 90095 EMAIL; Ruoxi Jiang Department of Computer Science University of Chicago Chicago, IL 60637 EMAIL; Quanquan Gu Department of Computer Science University of California, Los Angeles Los Angeles, CA 90095 EMAIL; Rebecca Willett Department of Statistics and Computer Science University of Chicago Chicago, IL 60637 EMAIL; Robert Nowak Department of Electrical and Computer Engineering University of Wisconsin-Madison Madison, WI 53706 EMAIL |
| Pseudocode | Yes | Algorithm 1 Arm Elimination with Adaptive Embedding and Induced Misspecification; Algorithm 2 Neural Arm Elimination |
| Open Source Code | No | The paper does not include a statement or link indicating that the source code for their methodology is publicly available. |
| Open Datasets | Yes | MNIST dataset [29] contains hand-written digits from 0 to 9. ... The MNIST database of handwritten digits. http://yann. lecun. com/exdb/mnist/, 1998. Yahoo dataset. The Yahoo! User Click Log Dataset R6A6 contains users click-through records. ... 6https://webscope.sandbox.yahoo.com |
| Dataset Splits | No | The paper describes sampling from datasets and the setup for pure exploration, but it does not specify explicit training, validation, and test dataset splits with percentages or sample counts typically used for model reproduction in supervised learning tasks. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers (e.g., 'Python 3.8, PyTorch 1.9') needed to replicate the experiments. |
| Experiment Setup | Yes | In our experiments, we set ϵ = 0.1 and δ = 0.05. All results are averaged over 50 runs. ... We first generate the feature matrix f X = X + E RK D where X is constructed as a rank-2 matrix and E is a perturbation matrix with tiny spectral norm (See Appendix G for details). |