cond-mat.mtrl-sci · 2026-08-20 · No. 90
Materials Science, 2026-08-20.
1 new papers in cond-mat.mtrl-sci. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
1 entries-
01
A single design choice determines whether machine learning models of materials make physically impossible predictions
Can Polat, Mustafa Kurban, Erchin Serpedin, Hasan Kurban
cond-mat.mtrl-sci · cs.LG · physics.comp-ph · quant-ph
Machine-learned models are replacing first-principles calculations across materials discovery, and physical symmetry is the central guarantee built into them. The debate over how much symmetry to hard-wire rather than learn has run on rotations, where a symmetry error is an approximation error. Some constraints are exact: symmetry forces certain property tensors to exactly zero, so a nonzero prediction is physically impossible rather than...
This edition is part of The Daily Abstract — cond-mat.mtrl-sci 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.