Research map / Optimization / Nonconvex and smooth optimization
Particle Dual Averaging: Optimization of Mean Field Neural Network with Global Convergence Rate Analysis
Atsushi Nitanda, Denny Wu, 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 |
|---|---|---|---|
| run PDA on a single-index regression teacher with resampled updates | PDA · synthetic student-teacher regression | objective convergence rate | Improved |
| train two-layer tanh network in mean field scaling (alpha=1) with PDA on concentric circles | PDA · make_circles binary classification | feature learning | Improved |
| optimize odd vs even MNIST with PDA (n=2500, width 2500) | PDA · MNIST odd vs even | generalization and convergence rate | Mixed |
Closest papers by meaning
- Improved Particle Approximation Error for Mean Field Neural Networks (NeurIPS 2024 · similarity 0.89)
- Mean-Field Langevin Dynamics for Signed Measures via a Bilevel Approach (NeurIPS 2024 · similarity 0.87)
- Convergence of Mean-Field Langevin Stochastic Descent-Ascent for Distributional Minimax Optimization (ICML 2025 · similarity 0.87)
- Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems (ICLR 2024 · similarity 0.87)
- Mean-field Underdamped Langevin Dynamics and its Spacetime Discretization (ICML 2024 · similarity 0.86)
- Mean-field Analysis on Two-layer Neural Networks from a Kernel Perspective (ICML 2024 · similarity 0.86)
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.
