AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Model, sample, and epoch-wise descents: exact solution of gradient flow in the random feature model

Antoine Bodin, Nicolas Macris

NeurIPS 2021 · Optimization › Implicit bias and generalization · approach: Neural tangent kernel analysis · 2 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
stop gradient-flow training at an earlier time rather than using the minimum least-squares estimatorrandom feature model near the interpolation threshold · model-wise double descenttest errorImproved
vary the number of model parameters across the interpolation thresholdrandom feature model during gradient flow · model-wise double descenttest errorMixed
vary the number of training samples across the interpolation thresholdrandom feature model during gradient flow · sample-wise double descenttest errorMixed
train over time in the largely overparameterized regimerandom feature model with ψ ≫ φ · epoch-wise descenttest errorMixed
use small regularization in the described noisy, overparameterized settingrandom feature model with ψ = 2φ · epoch-wise double descenttest errorMixed
vary sample size and model size so both interpolation conditions are encounteredrandom feature model at large training time · triple descenttest errorMixed

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