Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality

Authors: Teodor Vanislavov Marinov, Mehryar Mohri, Julian Zimmert

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This work is theoretical and it is hard to judge societal impact. If you are including theoretical results... Did you state the full set of assumptions of all theoretical results? [Yes] Please refer to the results in the stated theorems. Did you include complete proofs of all theoretical results? [Yes] Please refer to the appendix for complete proofs of the main results. If you ran experiments... [N/A] There is no code available for this work.
Researcher Affiliation Collaboration Teodor V. Marinov Google Research tvmarinov@google.com Mehryar Mohri Google Research & Courant Institute mohri@google.com Julian Zimmert Google Research zimmert@google.com
Pseudocode Yes Algorithm 1: Algorithm based on LP3
Open Source Code No There is no code available for this work.
Open Datasets No The paper is theoretical and does not conduct experiments on datasets. It defines theoretical assumptions about reward distributions (e.g., Gaussian or sub-Gaussian) but does not use or provide access to any specific dataset for training.
Dataset Splits No The paper does not describe any training, validation, or test dataset splits as it is a theoretical paper and does not involve empirical experiments.
Hardware Specification No The paper is theoretical and does not describe hardware used to run experiments.
Software Dependencies No The paper is theoretical and does not mention specific software dependencies with version numbers as it does not report empirical experiments.
Experiment Setup No The paper is theoretical and does not include details about an experimental setup, hyperparameters, or training configurations.