Research map / Optimization / Nonconvex and smooth optimization
Global Non-convex Optimization with Discretized Diffusions
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 a state-dependent diffusion instead of Langevin | Sublinear-growth objective f(x)=c log(1+||x||²/2) · Non-convex optimization example | optimization convergence | Helped |
| Use a non-constant diffusion coefficient tailored to the objective | Heavy-tailed and linear-growth non-convex objectives · Global non-convex optimization | global optimization applicability | Helped |
| Target a generalized Gibbs distribution with θ<1 instead of the standard Gibbs distribution | Discretized diffusion optimization · Expected suboptimality | expected suboptimality bound | Helped |
Closest papers by meaning
- Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimization (NeurIPS 2018 · similarity 0.90)
- Generalization of noisy SGD in unbounded non-convex settings (ICML 2025 · similarity 0.88)
- Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited (ICLR 2024 · similarity 0.87)
- Non-geodesically-convex optimization in the Wasserstein space (NeurIPS 2024 · similarity 0.87)
- The Poisson Midpoint Method for Langevin Dynamics: Provably Efficient Discretization for Diffusion Models (NeurIPS 2024 · similarity 0.86)
- Nearly $d$-Linear Convergence Bounds for Diffusion Models via Stochastic Localization (ICLR 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.