Unlearnable phases of matter

• URL: http://arxiv.org/abs/2602.11262v1
• Date: Wed, 11 Feb 2026 19:00:01 GMT
• Title: Unlearnable phases of matter
• Authors: Tarun Advaith Kumar, Yijian Zou, Amir-Reza Negari, Roger G. Melko, Timothy H. Hsieh,
• Abstract summary: We show that autoregressive neural networks fail to learn global properties of distributions characterized by locally indistinguishable (LI) states.<n>By introducing a restricted statistical query model, we prove that nontrivial phases with long-range CMI, such as strong-to-weak spontaneous symmetry breaking phases, are hard to learn.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We identify fundamental limitations in machine learning by demonstrating that non-trivial mixed-state phases of matter are computationally hard to learn. Focusing on unsupervised learning of distributions, we show that autoregressive neural networks fail to learn global properties of distributions characterized by locally indistinguishable (LI) states. We demonstrate that conditional mutual information (CMI) is a useful diagnostic for LI: we show that for classical distributions, long-range CMI of a state implies a spatially LI partner. By introducing a restricted statistical query model, we prove that nontrivial phases with long-range CMI, such as strong-to-weak spontaneous symmetry breaking phases, are hard to learn. We validate our claims by using recurrent, convolutional, and Transformer neural networks to learn the syndrome and physical distributions of toric/surface code under bit flip noise. Our findings suggest hardness of learning as a diagnostic tool for detecting mixed-state phases and transitions and error-correction thresholds, and they suggest CMI and more generally ``non-local Gibbsness'' as metrics for how hard a distribution is to learn.

Related papers

• Establishing Causal Relationship Between Whole Slide Image Predictions and Diagnostic Evidence Subregions in Deep Learning [3.5504159526793924]
  Causal Inference Multiple Instance Learning (CI-MIL) uses out-of-distribution generalization to reduce the recognition confusion of sub-images.<n>CI-MIL exhibits superior interpretability, as its selected regions demonstrate high consistency with ground truth annotations.
  arXiv  Detail & Related papers  (2024-07-24T11:00:08Z)
• Interpretability of Uncertainty: Exploring Cortical Lesion Segmentation in Multiple Sclerosis [33.91263917157504]
  Uncertainty quantification (UQ) has become critical for evaluating the reliability of artificial intelligence systems. This study addresses the interpretability of instance-wise uncertainty values in deep learning models for focal lesion segmentation in magnetic resonance imaging.
  arXiv  Detail & Related papers  (2024-07-08T09:13:30Z)
• Characterizing out-of-distribution generalization of neural networks: application to the disordered Su-Schrieffer-Heeger model [38.79241114146971]
  We show how interpretability methods can increase trust in predictions of a neural network trained to classify quantum phases. In particular, we show that we can ensure better out-of-distribution generalization in the complex classification problem. This work is an example of how the systematic use of interpretability methods can improve the performance of NNs in scientific problems.
  arXiv  Detail & Related papers  (2024-06-14T13:24:32Z)
• Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy [55.014926694758195]
  Entropy and mutual information in neural networks provide rich information on the learning process. We leverage data geometry to access the underlying manifold and reliably compute these information-theoretic measures. We show that they form noise-resistant measures of intrinsic dimensionality and relationship strength in high-dimensional simulated data.
  arXiv  Detail & Related papers  (2023-12-04T01:32:42Z)
• Learning Invariant Molecular Representation in Latent Discrete Space [52.13724532622099]
  We propose a new framework for learning molecular representations that exhibit invariance and robustness against distribution shifts. Our model achieves stronger generalization against state-of-the-art baselines in the presence of various distribution shifts.
  arXiv  Detail & Related papers  (2023-10-22T04:06:44Z)
• Attend Who is Weak: Pruning-assisted Medical Image Localization under Sophisticated and Implicit Imbalances [102.68466217374655]
  Deep neural networks (DNNs) have rapidly become a textitde facto choice for medical image understanding tasks. In this paper, we propose to use pruning to automatically and adaptively identify textithard-to-learn (HTL) training samples. We also present an interesting demographic analysis which illustrates HTLs ability to capture complex demographic imbalances.
  arXiv  Detail & Related papers  (2022-12-06T00:32:03Z)
• Detecting Shortcut Learning for Fair Medical AI using Shortcut Testing [62.9062883851246]
  Machine learning holds great promise for improving healthcare, but it is critical to ensure that its use will not propagate or amplify health disparities. One potential driver of algorithmic unfairness, shortcut learning, arises when ML models base predictions on improper correlations in the training data. Using multi-task learning, we propose the first method to assess and mitigate shortcut learning as a part of the fairness assessment of clinical ML systems.
  arXiv  Detail & Related papers  (2022-07-21T09:35:38Z)
• Learning from Heterogeneous Data Based on Social Interactions over Graphs [58.34060409467834]
  This work proposes a decentralized architecture, where individual agents aim at solving a classification problem while observing streaming features of different dimensions. We show that the. strategy enables the agents to learn consistently under this highly-heterogeneous setting. We show that the. strategy enables the agents to learn consistently under this highly-heterogeneous setting.
  arXiv  Detail & Related papers  (2021-12-17T12:47:18Z)
• Reducing Catastrophic Forgetting in Self Organizing Maps with Internally-Induced Generative Replay [67.50637511633212]
  A lifelong learning agent is able to continually learn from potentially infinite streams of pattern sensory data. One major historic difficulty in building agents that adapt is that neural systems struggle to retain previously-acquired knowledge when learning from new samples. This problem is known as catastrophic forgetting (interference) and remains an unsolved problem in the domain of machine learning to this day.
  arXiv  Detail & Related papers  (2021-12-09T07:11:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.