AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Learning Trajectories are Generalization Indicators

Jingwen Fu, Zhizheng Zhang, Dacheng Yin, Yan Lu, Nanning Zheng

NeurIPS 2023 · Optimization › Implicit bias and generalization · approach: Stability-based generalization 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
Use the proposed generalization bound instead of the compared stability-based boundToy dataset · Toy datasetgeneralization error bound: 3.62 vs 4.04Improved
Use the proposed generalization bound instead of the compared stability-based boundToy dataset · Toy datasetgeneralization error bound: 3.62 vs 4417Improved
Increase label noiseLearning trajectory complexity term and model · CIFAR-10generalization errorHurt
Increase learning rateLearning trajectory complexity term and model · CIFAR-10generalization errorImproved
Increase learning rateLearning trajectory complexity term · CIFAR-10C(J_t)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