paper-with-me

Papers

Attention to Order: Transformers Discover Phase Transitions via Learnability

2025-10-08 · Şener Özönder arxiv

Phase transitions mark qualitative reorganizations of collective behavior, yet identifying their boundaries remains challenging whenever analytic solutions are absent and conventional simulations fail. Here we introduce learnability as a universal criterion, defined as the ability of a transformer model containing attention mechanism to extract structure from microscopic states. Using self-supervised learning and Monte Carlo generated configurations of the two-dimensional Ising model, we show that ordered phases correspond to enhanced learnability, manifested in both reduced training loss and structured attention patterns, while disordered phases remain resistant to learning. Two unsupervised diagnostics, the sharp jump in training loss and the rise in attention entropy, recover the critical temperature in excellent agreement with the exact value. Our results establish learnability as a data-driven marker of phase transitions and highlight deep parallels between long-range order in condensed matter and the emergence of structure in modern language models.

📄 PDF Abstract BibTeX arXiv:2510.07401

Code (0)

등록된 구현이 없습니다.

Tasks

Self-Supervised Learning

Similar Papers 제목 키워드 기반

Discovering Phase Transitions with Unsupervised Learning

2016-06-01 · Lei Wang

Unsupervised learning is a discipline of machine learning which aims at discovering patterns in big data sets or classifying the data into several categories without being trained explicitly. We show that unsupervised le…

Clustering

Phase Transitions in Attention: A Bayesian Theory of Copy Head Emergence

2026-06-10 · Itay Lavie, Kirsten Fischer, Andrey Lekov, Frederic Van Maele 외 arxiv

Attention is the key mechanism underlying in-context learning in transformers, and attention patterns have been observed empirically to emerge abruptly during training. We present a Bayesian theory of feature learning in…

Unsupervised machine learning of quantum phase transitions using diffusion maps

2020-03-16 · Alexander Lidiak, Zhexuan Gong

Experimental quantum simulators have become large and complex enough that discovering new physics from the huge amount of measurement data can be quite challenging, especially when little theoretical understanding of the…

BIG-bench Machine LearningClusteringDimensionality Reduction

Interpretable Phase Detection and Classification with Persistent Homology

2020-12-01 · NeurIPS Workshop TDA_and_Beyond 2020 12 · Alex Cole, Gregory J. Loges, Gary Shiu

We apply persistent homology to the task of discovering and characterizing phase transitions, using lattice spin models from statistical physics for working examples. Persistence images provide a useful representation of…

ClassificationGeneral Classificationregression

Phase Transitions for the Information Bottleneck in Representation Learning

2020-01-07 · ICLR 2020 1 · Tailin Wu, Ian Fischer

In the Information Bottleneck (IB), when tuning the relative strength between compression and prediction terms, how do the two terms behave, and what's their relationship with the dataset and the learned representation? …

Representation Learning