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].
A Fisher-Rao gradient flow for entropic mean-field min-max games
Authors: Razvan-Andrei Lascu, Mateusz B. Majka, Lukasz Szpruch
TMLR 2024 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We examine the convergence in continuous-time of a Fisher-Rao (Mean-Field Birth-Death) gradient flow in the context of solving convex-concave min-max games with entropy regularization. We propose appropriate Lyapunov functions to demonstrate convergence with explicit rates to the unique mixed Nash equilibrium. |
| Researcher Affiliation | Academia | Razvan-Andrei Lascu EMAIL School of Mathematical and Computer Sciences, Heriot-Watt University, Edinburgh, UK, and Maxwell Institute for Mathematical Sciences, Edinburgh, UK Mateusz B. Majka EMAIL School of Mathematical and Computer Sciences, Heriot-Watt University, Edinburgh, UK, and Maxwell Institute for Mathematical Sciences, Edinburgh, UK Łukasz Szpruch EMAIL School of Mathematics, University of Edinburgh, UK, and The Alan Turing Institute, UK and Simtopia, UK |
| Pseudocode | No | The paper describes the Fisher-Rao gradient flow through mathematical equations (e.g., (5) and (19)) and provides theoretical analysis, but it does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain any explicit statements or links indicating that source code for the described methodology is provided or publicly available. |
| Open Datasets | No | The paper is theoretical, focusing on mathematical analysis of gradient flows and convergence. It does not perform empirical studies or use specific datasets for experimentation. |
| Dataset Splits | No | The paper is theoretical and does not conduct experiments with datasets, thus there is no mention of dataset splits. |
| Hardware Specification | No | The paper is theoretical and does not involve experimental computations, thus no hardware specifications are mentioned. |
| Software Dependencies | No | The paper is theoretical and does not describe any software implementation or specific software dependencies with version numbers. |
| Experiment Setup | No | The paper is purely theoretical, focusing on mathematical analysis and proofs. It does not include any experimental setup details, hyperparameters, or training configurations. |