AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev

Xiao Wang, Qi Lei, Ioannis Panageas

NeurIPS 2020 · Optimization › Nonconvex and smooth optimization · approach: Langevin sampling for nonconvex problems

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 changedWhereMeasuredEffect
Use the exponential map to update points along manifold geodesicsGeodesic Langevin Algorithm (GLA) · Closed Riemannian manifoldKL 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 inequalityRiemannian Langevin equation · Closed Riemannian manifoldKL divergence: H(\rho_t|\nu)\le e^{-2\alpha t}H(\rho_0|\nu)Improved
Choose the GLA stepsize to control discretization biasGeodesic Langevin Algorithm (GLA) · Closed Riemannian manifoldWasserstein 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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy