all AI news
Beyond Lipschitz: Sharp Generalization and Excess Risk Bounds for Full-Batch GD. (arXiv:2204.12446v1 [stat.ML])
April 27, 2022, 1:12 a.m. | Konstantinos E. Nikolakakis, Farzin Haddadpour, Amin Karbasi, Dionysios S. Kalogerias
cs.LG updates on arXiv.org arxiv.org
We provide sharp path-dependent generalization and excess error guarantees
for the full-batch Gradient Decent (GD) algorithm for smooth losses (possibly
non-Lipschitz, possibly nonconvex). At the heart of our analysis is a novel
generalization error technique for deterministic symmetric algorithms, that
implies average output stability and a bounded expected gradient of the loss at
termination leads to generalization. This key result shows that small
generalization error occurs at stationary points, and allows us to bypass
Lipschitz assumptions on the loss prevalent …
More from arxiv.org / cs.LG updates on arXiv.org
A Single-Loop Algorithm for Decentralized Bilevel Optimization
1 day, 9 hours ago |
arxiv.org
CLEANing Cygnus A deep and fast with R2D2
1 day, 9 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Data Management Associate
@ EcoVadis | Ebène, Mauritius
Senior Data Engineer
@ Telstra | Telstra ICC Bengaluru