cond-mat.dis-nn · 2026-07-30 · No. 69
Disordered Systems and Neural Networks, 2026-07-30.
1 new papers in cond-mat.dis-nn. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
1 entries-
01
On the robustness of noisy solutions in non-convex neural networks
Enrico M. Malatesta, Alessandra Passalacqua, Riccardo Zecchina
cond-mat.dis-nn · cs.LG · math.PR
Optimization in non-convex neural network models is strongly influenced by the geometry of the solution space: sparse, isolated, point-like clusters are typically algorithmically inaccessible, whereas wide and flat regions can be found efficiently despite being relatively rare. At zero temperature this picture has been formalized in binary perceptrons through the overlap gap property (OGP), which limits algorithmic access to configurations...
This edition is part of The Daily Abstract — cond-mat.dis-nn archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.