AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics

Taiji Suzuki

NeurIPS 2020 · Optimization › Implicit bias and generalization · approach: Gradient flow and mean-field dynamics · 11 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
Formulate training as transportation-map estimation and use infinite-dimensional Langevin dynamicsNeural network training · Finite-width and infinite-width networksglobal convergenceImproved
Use transportation-map GLD for estimationNeural network regression · Regressionexcess risk rate: n^{-2 b/(2a + d )}Improved
Use transportation-map GLD under the strong low-noise and realizability assumptionsNeural network classification · Binary classificationclassification error probability: \exp(- c' \beta \delta^{\tfrac{2m}{2m-d}})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