all AI news
Learning time-scales in two-layers neural networks
April 19, 2024, 4:42 a.m. | Rapha\"el Berthier, Andrea Montanari, Kangjie Zhou
cs.LG updates on arXiv.org arxiv.org
Abstract: Gradient-based learning in multi-layer neural networks displays a number of striking features. In particular, the decrease rate of empirical risk is non-monotone even after averaging over large batches. Long plateaus in which one observes barely any progress alternate with intervals of rapid decrease. These successive phases of learning often take place on very different time scales. Finally, models learnt in an early phase are typically `simpler' or `easier to learn' although in a way that …
abstract arxiv cs.lg features gradient layer math.oc networks neural networks progress rate risk stat.ml type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead Data Engineer
@ WorkMoney | New York City, United States - Remote