Adaptive Oracle-Efficient Online Learning
Authors: Guanghui Wang, Zihao Hu, Vidya Muthukumar, Jacob D. Abernethy
NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | Did you run experiments? [N/A] |
| Researcher Affiliation | Academia | Guanghui Wang , Zihao Hu , Vidya Muthukumar , , Jacob Abernethy College of Computing School of Electrical and Computer Engineering School of Industrial and Systems Engineering Georgia Institute of Technology Atlanta, GA 30339 {gwang369,zihaohu,vmuthukumar8,prof}@gatech.edu |
| Pseudocode | Yes | Algorithm 1 Generalized follow-the-perturbed-leader with small-loss bound" and "Algorithm 3 Oracle-efficient Flipflop (OFF) |
| Open Source Code | No | Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [N/A] |
| Open Datasets | No | The paper is theoretical and does not report experimental results that would involve training on specific datasets. The checklist explicitly states 'N/A' for questions related to experiments and data. |
| Dataset Splits | No | The paper is theoretical and does not report experimental results that would involve dataset splits. The checklist explicitly states 'N/A' for questions related to experiments and data. |
| Hardware Specification | No | The paper is theoretical and does not report experimental results, hence no hardware specifications are provided. The checklist explicitly states 'N/A' for questions about computing resources. |
| Software Dependencies | No | The paper is theoretical and does not report experimental results. Therefore, no specific software versions or dependencies are mentioned for reproducibility. The checklist explicitly states 'N/A' for questions about training details. |
| Experiment Setup | No | The paper is theoretical and does not report experimental results, so no specific experimental setup details like hyperparameters or training configurations are provided. The checklist explicitly states 'N/A' for questions about training details. |