Finite-Time Last-Iterate Convergence for Learning in Multi-Player Games

Authors: Yang Cai, Argyris Oikonomou, Weiqiang Zheng

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

Reproducibility Variable Result LLM Response
Research Type Theoretical Our results are theoretical. We state the assumptions of our results in the statements of the lemmas. If you ran experiments... [N/A]
Researcher Affiliation Academia Yang Cai Yale University yang.cai@yale.edu Argyris Oikonomou Yale University argyris.oikonomou@yale.edu Weiqiang Zheng Yale University weiqiang.zheng@yale.edu
Pseudocode No The algorithms (Optimistic Gradient and Extragradient) are described using mathematical equations (e.g., 'zk = ΠZ [zk 1 ηF(wk)] , wk+1 = ΠZ [zk ηF(wk)] (1)') rather than formal pseudocode blocks or algorithm boxes.
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 involve experiments or datasets for training. The reproducibility checklist states 'N/A' for experimental results.
Dataset Splits No The paper is theoretical and does not involve experiments or dataset splits for validation. The reproducibility checklist states 'N/A' for experimental results.
Hardware Specification No The paper is theoretical and does not mention any specific hardware used for experiments. The reproducibility checklist states 'N/A' for experimental results.
Software Dependencies No The paper mentions 'SOS programming' but does not list specific software dependencies with version numbers for experimental setup. The reproducibility checklist states 'N/A' for experimental results.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with hyperparameters or training configurations. The reproducibility checklist states 'N/A' for experimental results.