Bridging Control, Inference, Transport, and Thermodynamics: From Theory to Applications in Learning

• URL: http://arxiv.org/abs/2609.15897v1
• Date: Mon, 14 Sep 2026 17:16:33 GMT
• Title: Bridging Control, Inference, Transport, and Thermodynamics: From Theory to Applications in Learning
• Abstract summary: The last decade has seen the development of powerful methods for learning complex structure from high-dimensional data.<n>These advances have brought to the foreground fundamental connections between subdisciplines of physics, applied mathematics, and machine learning.<n>We highlight a conceptual thread that links five distinct fields: control theory, optimal transport, probabilistic inference, non-equilibrium thermodynamics, and machine learning.
• Score: 25.727025115930825
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The last decade has seen the development of powerful methods for learning complex structure from high-dimensional data. These advances have brought to the foreground fundamental connections between subdisciplines of physics, applied mathematics, and machine learning. In this review, we bring together some of these ideas, often expressed in different languages, to highlight a conceptual thread that links five distinct fields: control theory, optimal transport, probabilistic inference, non-equilibrium thermodynamics, and machine learning. A common theme is the optimization of free-energy-like functionals under dynamical or statistical constraints. We offer a guided tour through this thread and present selected applications in reinforcement learning, variational inference, and generative modeling. The review does not assume prior familiarity with these topics, and begins with principles originating from physics.

Related papers

• Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes [57.55143519213221]
  We provide empirical clarity through a systematic exploration of multimodal pretraining.<n>Our experiments on both synthetic and large-scale real-world datasets yield four key insights into the physics of multimodal pretraining.
  arXiv  Detail & Related papers  (2026-08-05T16:09:25Z)
• Invariant Learning Dynamics of Transformers in Inductive Reasoning Tasks [50.79340930913805]
  We study a class of inductive tasks that unifies several synthetic tasks known in the literature, including in-context n-grams and multi-hop reasoning.<n>By casting circuit formation as a low-dimensional dynamical phenomenon, we take a step toward a predictive theory of how Transformers learn.
  arXiv  Detail & Related papers  (2026-07-13T17:56:11Z)
• There Will Be a Scientific Theory of Deep Learning [62.690977616250954]
  We make the case that a scientific theory of deep learning is emerging.<n>We identify five growing bodies of work that point toward such a theory.<n>We argue that the emerging theory is best thought of as a mechanics of the learning process.
  arXiv  Detail & Related papers  (2026-04-23T13:58:12Z)
• Learning About Learning: A Physics Path from Spin Glasses to Artificial Intelligence [0.0]
  The Hopfield model, originally inspired by spin-glass physics, occupies a central place at the intersection of statistical mechanics, neural networks, and modern artificial intelligence.<n>We present the Hopfield model as a pedagogically rich framework that naturally unifies core topics from undergraduate statistical physics, dynamical systems, linear algebra, and computational methods.<n>This work aims to help students understand, apply, and critically engage with the computational tools increasingly central to research, industry, and society.
  arXiv  Detail & Related papers  (2026-01-12T15:16:15Z)
• Understanding Machine Learning Paradigms through the Lens of Statistical Thermodynamics: A tutorial [0.0]
  The tutorial delves into advanced techniques like entropy, free energy, and variational inference which are utilized in machine learning. We show how an in-depth comprehension of physical systems' behavior can yield more effective and dependable machine learning models.
  arXiv  Detail & Related papers  (2024-11-24T18:20:05Z)
• Foundations and Frontiers of Graph Learning Theory [81.39078977407719]
  Recent advancements in graph learning have revolutionized the way to understand and analyze data with complex structures. Graph Neural Networks (GNNs), i.e. neural network architectures designed for learning graph representations, have become a popular paradigm. This article provides a comprehensive summary of the theoretical foundations and breakthroughs concerning the approximation and learning behaviors intrinsic to prevalent graph learning models.
  arXiv  Detail & Related papers  (2024-07-03T14:07:41Z)
• Constructing Custom Thermodynamics Using Deep Learning [10.008895786910195]
  One of the most exciting applications of artificial intelligence (AI) is automated scientific discovery based on previously amassed data. Here we develop a platform based on a generalized Onsager principle to learn macroscopic descriptions of arbitrary dissipative systems. We demonstrate its effectiveness by studying theoretically and experimentally validating the stretching of long polymer chains in an externally applied field.
  arXiv  Detail & Related papers  (2023-08-08T08:19:43Z)
• Symmetry Group Equivariant Architectures for Physics [52.784926970374556]
  In the domain of machine learning, an awareness of symmetries has driven impressive performance breakthroughs. We argue that both the physics community and the broader machine learning community have much to understand.
  arXiv  Detail & Related papers  (2022-03-11T18:27:04Z)
• The problem of engines in statistical physics [62.997667081978825]
  Engines are open systems that can generate work cyclically, at the expense of an external disequilibrium. Recent advances in the theory of open quantum systems point to a more realistic description of autonomous engines. We show how the external loading force and the thermal noise may be incorporated into the relevant equations of motion.
  arXiv  Detail & Related papers  (2021-08-17T03:59:09Z)
• Physics guided machine learning using simplified theories [0.0]
  Recent applications of machine learning, in particular deep learning, motivate the need to address the generalizability of the statistical inference approaches in physical sciences. We introduce a modular physics guided machine learning framework to improve the accuracy of such data-driven predictive engines.
  arXiv  Detail & Related papers  (2020-12-18T21:30:40Z)

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.