Research map / Optimization / Nonconvex and smooth optimization
Accelerating optimization over the space of probability measures
Shi Chen, Qin Li, Oliver Tse, Stephen J. Wright
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 |
|---|---|---|---|
| replace Wasserstein gradient flow with heavy-ball, Nesterov or exponentially convergent variational acceleration flow | Wasserstein gradient flow · Potential energy V1 and V2 (d=500 and d=200, N=100 particles) | optimality gap over continuous time | Improved |
| use Nesterov and Hamiltonian flows instead of Wasserstein gradient flow | Wasserstein gradient flow · Potential energy V1 and V2 (d=500 and d=200, N=100 particles) | total number of solver steps at small tolerance | Improved |
Closest papers by meaning
- Breaking the Convergence Barrier: Optimization via Fixed-Time Convergent Flows (AAAI 2022 · similarity 0.91)
- Hamiltonian Descent Algorithms for Optimization: Accelerated Rates via Randomized Integration Time (NeurIPS 2025 · similarity 0.90)
- Optimization with Momentum: Dynamical, Control-Theoretic, and Symplectic Perspectives (JMLR 2021 · similarity 0.88)
- Accelerating Optimization via Differentiable Stopping Time (NeurIPS 2025 · similarity 0.88)
- Perfect Parallelization in Mini-Batch SGD with Classical Momentum Acceleration (NeurIPS 2026 · similarity 0.88)
- Optimizing $(L_0, L_1)$-Smooth Functions by Gradient Methods (ICLR 2025 · 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.
