Research map / Optimization / Implicit bias and generalization
On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use particle gradient flow with a suitably initialized, over-parameterized particle distribution instead of optimizing only particle weights on a fixed grid | Particle gradient flow · Synthetic sparse deconvolution, ReLU, and sigmoid experiments | excess loss | Helped |
| Increase particle count from 6 to 10 or 100 | Particle gradient flow · Sparse deconvolution on the 1-torus | global minimizer found: 6; 10; 100 | Helped |
| Increase neuron count from 5 to 10 or 100 | Particle gradient flow · ReLU network, d=2 | global minimizer found: 5; 10; 100 | Helped |
Closest papers by meaning
- Neural Wasserstein Gradient Flows for Discrepancies with Riesz Kernels (ICML 2023 · similarity 0.89)
- MinMax Methods for Optimal Transport and Beyond: Regularization, Approximation and Numerics (NeurIPS 2020 · similarity 0.89)
- The Sparse-Plus-Low-Rank Quasi-Newton Method for Entropic-Regularized Optimal Transport (ICML 2025 · similarity 0.88)
- Global Minimizers of $\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks (NeurIPS 2025 · similarity 0.88)
- Decreasing Entropic Regularization Averaged Gradient for Semi-Discrete Optimal Transport (NeurIPS 2025 · similarity 0.88)
- Safe and Sparse Newton Method for Entropic-Regularized Optimal Transport (NeurIPS 2024 · similarity 0.87)
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.