AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Learning Globally Smooth Functions on Manifolds

Juan Cervino, Luiz F. O. Chamon, Benjamin David Haeffele, Rene Vidal, Alejandro Ribeiro

ICML 2023 · Optimization › Nonconvex and smooth optimization · approach: Coordinate and Adam convergence analysis · 1 citations (OpenAlex)

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
Manifold Lipschitz constraint (dual weighted Laplacian) instead of ERMground robot error prediction · Grass and Pavementerror (lower is better): 0.42 to 0.25 (Grass); 0.0120 to 0.0032 (Pavement)Improved
Ambient Lipschitz regularization instead of ERMquadrotor state prediction · unseen test trajectoryerror (lower is better): 0.00666 to 0.00734Hurt
Manifold Laplacian regularization instead of ERMquadrotor state prediction · unseen test trajectoryerror (lower is better): 0.00666 to 0.00625Improved
Manifold Lipschitz constraint instead of ERMquadrotor state prediction · unseen test trajectoryerror (lower is better): 0.00666 to 0.00237Improved
Manifold Lipschitz constraint instead of manifold regularizationground robot and quadrotor · Grass, Pavement, quadrotor testerror (lower is better): Grass 0.38 to 0.25; Pavement 0.0045 to 0.0032; quadrotor 0.00625 to 0.00237Improved
Ambient Lipschitz regularization instead of ERM on ground robotground robot error prediction · Grass and Pavementerror (lower is better): 0.42 to 0.31 (Grass); 0.0120 to 0.0065 (Pavement)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