Research map / Optimization / Nonconvex and smooth optimization
Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev
Xiao Wang, Qi Lei, Ioannis Panageas
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 |
|---|---|---|---|
| Use the exponential map to update points along manifold geodesics | Geodesic Langevin Algorithm (GLA) · Closed Riemannian manifold | KL divergence: H(p_k|\nu)\le e^{-\alpha k\epsilon}H(p_0|\nu)+\frac{16\epsilon}{3\alpha}(2nL^2+2n^3K_2C+nK_3K_4) | Improved |
| Assume the target distribution satisfies a log-Sobolev inequality | Riemannian Langevin equation · Closed Riemannian manifold | KL divergence: H(\rho_t|\nu)\le e^{-2\alpha t}H(\rho_0|\nu) | Improved |
| Choose the GLA stepsize to control discretization bias | Geodesic Langevin Algorithm (GLA) · Closed Riemannian manifold | Wasserstein distance squared: W_2(\rho_k,\nu)^2\le\frac{2}{\alpha}e^{-\alpha k\epsilon}H(p_0|\nu)+\frac{32\epsilon}{3\alpha^2}(2nL^2+2n^3K_2C+nK_3K_4) | Improved |
Closest papers by meaning
- Efficient Sampling on Riemannian Manifolds via Langevin MCMC (NeurIPS 2022 · similarity 0.90)
- Provable Convergence and Limitations of Geometric Tempering for Langevin Dynamics (ICLR 2025 · similarity 0.87)
- Non-asymptotic Error Bounds in $\mathcal{W}_2$-Distance with Sqrt(d) Dimension Dependence and First Order Convergence for Langevin Monte Carlo beyond Log-Concavity (ICML 2025 · similarity 0.86)
- The Noisy Laplacian: a Threshold Phenomenon for Non-Linear Dimension Reduction (ICML 2025 · similarity 0.86)
- Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited (ICLR 2024 · similarity 0.86)
- Generalization of noisy SGD in unbounded non-convex settings (ICML 2025 · 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.
