Skip to content
conftrace_

lazy training regime

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

feature learning (2) phase diagram (1) rich infinite-width regime (1) lazy training (1) neural network width (1) gradient orthogonality (1) network width (1) kernel machine (1) weight decay (1) learning dynamics (1)

Papers

Adaptive kernel predictors from feature-learning infinite limits of neural networks ICML 2025 Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning ICML 2023 Wide Neural Networks Forget Less Catastrophically ICML 2022