all AI news
Proving Linear Mode Connectivity of Neural Networks via Optimal Transport
March 4, 2024, 5:42 a.m. | Damien Ferbach, Baptiste Goujaud, Gauthier Gidel, Aymeric Dieuleveut
cs.LG updates on arXiv.org arxiv.org
Abstract: The energy landscape of high-dimensional non-convex optimization problems is crucial to understanding the effectiveness of modern deep neural network architectures. Recent works have experimentally shown that two different solutions found after two runs of a stochastic training are often connected by very simple continuous paths (e.g., linear) modulo a permutation of the weights. In this paper, we provide a framework theoretically explaining this empirical observation. Based on convergence rates in Wasserstein distance of empirical measures, …
abstract architectures arxiv connectivity continuous cs.lg deep neural network energy found landscape linear modern network networks neural network neural networks optimization simple solutions stochastic training transport type understanding via
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote