← Back to all news
arXiv Machine Learning By Can Polat, Mustafa Kurban, Erchin Serpedin, Hasan Kurban

A single design choice determines whether machine learning models of materials make physically impossible predictions

Read the original on arXiv Machine Learning →

The article demonstrates that a single design decision—whether a machine‑learning model’s features include parity labels—determines if the model can ever predict physically impossible values for material properties. Using group‑theoretical analysis, the authors introduce the parity gap criterion to identify which properties and crystal symmetries are affected. Experiments on 2,000 centrosymmetric crystals show that parity‑labelled models achieve exact zero predictions for forbidden piezoelectric responses, whereas models lacking parity labels produce large errors, yet both maintain comparable overall accuracy.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 17

The parity gap in crystal tensor prediction

arXiv:2608.18714v2 Announce Type: replace-cross Abstract: Crystal symmetry dictates whether a physical response tensor must vanish, establishing a direct test for machine learning predictions indepen...

By Can Polat, Mustafa Kurban, Erchin Serpedin, Hasan Kurban
benchmarks
More like this →
arXiv AI
Sep 15

Symmetry- and Property-Aware Crystal Generation with Reinforcement Learning for Inverse Materials Design

The paper introduces SPARC, a reinforcement learning framework that generates crystalline materials while respecting symmetry constraints essential for meaningful physical properties. SPARC is applied to two tasks: optimizing uniaxial dielectric anisotropy, which requires specific crystal classes, and maximizing spectroscopic limited maximum efficiency, a scalar objective that lets the algorithm discover suitable crystallographic motifs. The results demonstrate that symmetry is a foundational requirement for producing robust, realizable functional materials.

By Ting-Wei Hsu, Arun Bansil, Qimin Yan
reinforcement-learning
More like this →
arXiv AI
Sep 2

Autonomous discovery of new structure-plausibility laws for explainable and rapid crystal diagnosis and screening

The paper reports that autonomous agents can generate, test, and refute millions of candidate structure-plausibility laws, ultimately producing eight Plausibility Rules for Inorganic Structures (PRIS) that capture five key mechanisms of crystal stability. PRIS achieves high agreement with experimental structures (82–99%) and outperforms traditional Pauling rules, detecting damaged crystals with 87.9% accuracy and correlating strongly with synthesizability. By integrating PRIS with a synthesis score (PSS), the authors demonstrate significant reductions in expensive DFT validation and improved inverse-design efficiency, while also providing chemical explanations for failures and anomalies in crystal data.

By Zhilong Song, Lixue Cheng
agents
More like this →
arXiv Machine Learning
Jul 30

Exact Symmetry as Algebra: A Machine-Verified Tensor Calculus that Enforces Physical Selection Rules

arXiv:2605. 20440v2 Announce Type: replace Abstract: Symmetry is central to the physical sciences, yet machine learning usually captures it only approximately, leaving a residual per-step equivariance error $\varepsilon$ that compounds with depth $M$ as $M\varepsilon$, whereas exact equivariance holds at unbounded depth; we demonstrate this divergence at fourteen orders of magnitude.

By Paulina Hoyos, Shashanka Ubaru, Dongsung Huh, Vasileios Kalantzis, Kenneth L. Clarkson, Misha Kilmer, Haim Avron, Lior Horesh
More like this →