Research map / Optimization / Nonconvex and smooth optimization
Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems
Atsushi Nitanda, Kazusato Oko, Denny Wu, Nobuhito Takenouchi, Taiji Suzuki
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Store finite-sum empirical averages instead of all past particles | Efficient EFP · Finite-sum problems | memory cost across iterations | Improved |
| Increase the number of triangle particles | EFP image synthesis · Mona Lisa image synthesis | generated image quality | Improved |
| Use EFP to optimize the two-layer neural network | Two-layer neural network with tanh activation · Student-teacher experiment | primal-dual gap | Improved |
Closest papers by meaning
- Entropic Fictitious Play for Mean Field Optimization Problem (JMLR 2023 · similarity 0.92)
- Non-convex entropic mean-field optimization via Best Response flow (NeurIPS 2025 · similarity 0.86)
- Optimism Without Regularization: Constant Regret in Zero-Sum Games (NeurIPS 2025 · similarity 0.86)
- Extensive-Form Game Solving via Blackwell Approachability on Treeplexes (NeurIPS 2024 · similarity 0.84)
- Solving Neural Min-Max Games: The Role of Architecture, Initialization & Dynamics (NeurIPS 2025 · similarity 0.84)
- On the Optimality of Dilated Entropy and Lower Bounds for Online Learning in Extensive-Form Games (NeurIPS 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
