Why is topology hard to learn?

• URL: http://arxiv.org/abs/2509.26261v1
• Date: Tue, 30 Sep 2025 13:48:25 GMT
• Title: Why is topology hard to learn?
• Authors: D. O. Oriekhov, Stan Bergkamp, Guliuxin Jin, Juan Daniel Torres Luna, Badr Zouggari, Sibren van der Meer, Naoual El Yazidi, Eliska Greplova,
• Abstract summary: We bridge the concept of a physical quantity and its machine learning approximation in the context of the original application of neural networks in physics.<n>We construct a hybrid tensor-neural network object that exactly expresses real space topological invariant.<n>Our work highlights the challenges in learning topological invariants and constitutes a stepping stone towards more accurate and better generalizable machine learning representations in condensed matter physics.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Much attention has been devoted to the use of machine learning to approximate physical concepts. Yet, due to challenges in interpretability of machine learning techniques, the question of what physics machine learning models are able to learn remains open. Here we bridge the concept a physical quantity and its machine learning approximation in the context of the original application of neural networks in physics: topological phase classification. We construct a hybrid tensor-neural network object that exactly expresses real space topological invariant and rigorously assess its trainability and generalization. Specifically, we benchmark the accuracy and trainability of a tensor-neural network to multiple types of neural networks, thus exemplifying the differences in trainability and representational power. Our work highlights the challenges in learning topological invariants and constitutes a stepping stone towards more accurate and better generalizable machine learning representations in condensed matter physics.

Related papers

• Can Data-Driven Dynamics Reveal Hidden Physics? There Is A Need for Interpretable Neural Operators [10.591168773809635]
  We classify neural operators into two types: (1) Spatial domain models that learn on grids and (2) Functional domain models that learn with function bases.<n> Specifically, we provide a way to explain the prediction-making process of neural operators and show that neural operator can learn hidden physical patterns from data.<n>Next, we show that a simple dual-space multi-scale model can achieve SOTA performance and we believe that dual-space multi-spatio-scale models hold significant potential to learn complex physics.
  arXiv  Detail & Related papers  (2025-10-03T02:50:21Z)
• Machine Learning and Control: Foundations, Advances, and Perspectives [0.0]
  We show that concepts such as simultaneous and ensemble controllability offer new insights into the classification and representation properties of deep neural networks.<n>We also explore the relationship between dynamic and static neural networks, where depth is traded for width.<n>We describe how classical properties of diffusion processes, long established in the context of partial differential equations, contribute to explaining the success of modern generative artificial intelligence.
  arXiv  Detail & Related papers  (2025-09-30T10:47:26Z)
• High-entropy Advantage in Neural Networks' Generalizability [7.193952396909214]
  One of the central challenges in modern machine learning is understanding how neural networks generalize knowledge learned from training data to unseen test data.<n>Here we introduce the concept of Boltzmann entropy into neural networks as hypothetical molecular systems where weights and biases are atomic coordinates, and the loss function is the potential energy.<n>By employing molecular simulation algorithms, we compute entropy landscapes as functions of both training loss and test accuracy (or test loss) on networks with up to 1 million parameters, across four distinct machine learning tasks.
  arXiv  Detail & Related papers  (2025-03-17T13:16:25Z)
• Mechanistic Neural Networks for Scientific Machine Learning [58.99592521721158]
  We present Mechanistic Neural Networks, a neural network design for machine learning applications in the sciences. It incorporates a new Mechanistic Block in standard architectures to explicitly learn governing differential equations as representations. Central to our approach is a novel Relaxed Linear Programming solver (NeuRLP) inspired by a technique that reduces solving linear ODEs to solving linear programs.
  arXiv  Detail & Related papers  (2024-02-20T15:23:24Z)
• Gaussian Process Surrogate Models for Neural Networks [6.8304779077042515]
  In science and engineering, modeling is a methodology used to understand complex systems whose internal processes are opaque. We construct a class of surrogate models for neural networks using Gaussian processes. We demonstrate our approach captures existing phenomena related to the spectral bias of neural networks, and then show that our surrogate models can be used to solve practical problems.
  arXiv  Detail & Related papers  (2022-08-11T20:17:02Z)
• Privacy-preserving machine learning with tensor networks [37.01494003138908]
  We show that tensor network architectures have especially prospective properties for privacy-preserving machine learning. First, we describe a new privacy vulnerability that is present in feedforward neural networks, illustrating it in synthetic and real-world datasets. We rigorously prove that such conditions are satisfied by tensor-network architectures.
  arXiv  Detail & Related papers  (2022-02-24T19:04:35Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• Physics-informed ConvNet: Learning Physical Field from a Shallow Neural Network [0.180476943513092]
  Modelling and forecasting multi-physical systems remain a challenge due to unavoidable data scarcity and noise. New framework named physics-informed convolutional network (PICN) is recommended from a CNN perspective. PICN may become an alternative neural network solver in physics-informed machine learning.
  arXiv  Detail & Related papers  (2022-01-26T14:35:58Z)
• The Physics of Machine Learning: An Intuitive Introduction for the Physical Scientist [0.0]
  This article is intended for physical scientists who wish to gain deeper insights into machine learning algorithms. We begin with a review of two energy-based machine learning algorithms, Hopfield networks and Boltzmann machines, and their connection to the Ising model. We then delve into additional, more "practical," machine learning architectures including feedforward neural networks, convolutional neural networks, and autoencoders.
  arXiv  Detail & Related papers  (2021-11-27T15:12:42Z)
• Physics informed neural networks for continuum micromechanics [68.8204255655161]
  Recently, physics informed neural networks have successfully been applied to a broad variety of problems in applied mathematics and engineering. Due to the global approximation, physics informed neural networks have difficulties in displaying localized effects and strong non-linear solutions by optimization. It is shown, that the domain decomposition approach is able to accurately resolve nonlinear stress, displacement and energy fields in heterogeneous microstructures obtained from real-world $mu$CT-scans.
  arXiv  Detail & Related papers  (2021-10-14T14:05:19Z)
• A neural anisotropic view of underspecification in deep learning [60.119023683371736]
  We show that the way neural networks handle the underspecification of problems is highly dependent on the data representation. Our results highlight that understanding the architectural inductive bias in deep learning is fundamental to address the fairness, robustness, and generalization of these systems.
  arXiv  Detail & Related papers  (2021-04-29T14:31:09Z)
• Explainable artificial intelligence for mechanics: physics-informing neural networks for constitutive models [0.0]
  In mechanics, the new and active field of physics-informed neural networks attempts to mitigate this disadvantage by designing deep neural networks on the basis of mechanical knowledge. We propose a first step towards a physics-forming-in approach, which explains neural networks trained on mechanical data a posteriori. Therein, the principal component analysis decorrelates the distributed representations in cell states of RNNs and allows the comparison to known and fundamental functions.
  arXiv  Detail & Related papers  (2021-04-20T18:38:52Z)
• Learning Contact Dynamics using Physically Structured Neural Networks [81.73947303886753]
  We use connections between deep neural networks and differential equations to design a family of deep network architectures for representing contact dynamics between objects. We show that these networks can learn discontinuous contact events in a data-efficient manner from noisy observations. Our results indicate that an idealised form of touch feedback is a key component of making this learning problem tractable.
  arXiv  Detail & Related papers  (2021-02-22T17:33:51Z)
• Learning Connectivity of Neural Networks from a Topological Perspective [80.35103711638548]
  We propose a topological perspective to represent a network into a complete graph for analysis. By assigning learnable parameters to the edges which reflect the magnitude of connections, the learning process can be performed in a differentiable manner. This learning process is compatible with existing networks and owns adaptability to larger search spaces and different tasks.
  arXiv  Detail & Related papers  (2020-08-19T04:53:31Z)

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.