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 Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Robust Pure Exploration in Linear Bandits with Limited Budget
Authors: Ayya Alieva, Ashok Cutkosky, Abhimanyu Das
ICML 2021 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We complement our theoretical results with empirical validation. In this section, we empirically validate our approach via synthetic experiments. |
| Researcher Affiliation | Collaboration | 1Stanford University, Stanford, California, USA 2Boston University, Boston, Massachussetts, USA 3Google Research, Mountain View, California, USA. |
| Pseudocode | Yes | We provide the pseudocode for our pure exploration algorithm in Algorithms 1 and 2. |
| Open Source Code | No | The paper does not provide an explicit statement about the availability of source code for the described methodology or a link to a code repository. |
| Open Datasets | No | The paper describes synthetic experiments using self-generated data distributions (Uniform, Gaussian Mixture, Clusters, Subspace) but does not refer to a publicly available or open dataset with access information. |
| Dataset Splits | No | The paper does not specify dataset splits (e.g., train/validation/test percentages or counts) needed to reproduce data partitioning. It mentions using synthetic data averaged over trials, but not fixed splits. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running the experiments (e.g., GPU/CPU models, memory, or cloud instance types). |
| Software Dependencies | No | The paper does not provide specific software dependency details, such as library names with version numbers, to reproduce the experiments. |
| Experiment Setup | Yes | The experiments used d = 3, n = 50, T = 800, and are averaged over 200 trials. For instance, while the real σ and real η are both equal to 1.0 in our setting, the grey area was sampled from 0.5 to 3.0 for σ, and from 0.5 to 2.0 for η. |