cond-mat.stat-mech · 2026-09-09 · No. 110
Statistical Mechanics, 2026-09-09.
1 new papers in cond-mat.stat-mech. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
1 entries-
01
Speed Limit for Information Acquisition in Stochastic Learning Dynamics
Shuta Kobayashi, Andreas Dechant
cond-mat.stat-mech · cs.LG · stat.ML
Neural networks acquire internal representations through learning. In this work, we formulate stochastic gradient descent (SGD) as a Markovian stochastic process and derive a Fisher-information flow speed limit that bounds the rate at which trainable parameters can acquire information about latent variables in the data-generating process. The resulting inequality decomposes the information flow into drift and noise contributions, thereby...
This edition is part of The Daily Abstract — cond-mat.stat-mech 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.