English
Related papers

Related papers: Learning rate matrix and information-thermodynamic…

200 papers

How do organisms recognize their environment by acquiring knowledge about the world, and what actions do they take based on this knowledge? This article examines hypotheses about organisms' adaptation to the environment from machine…

Neurons and Cognition · Quantitative Biology 2019-03-01 Hideaki Shimazaki

A basic task of information processing is information transfer (flow). Here we study a pair of Brownian particles each coupled to a thermal bath at temperature $T_1$ and $T_2$, respectively. The information flow in such a system is defined…

Statistical Mechanics · Physics 2015-05-13 Armen E. Allahverdyan , Dominik Janzing , Guenter Mahler

We have formulated a family of machine learning problems as the time evolution of Parametric Probabilistic Models (PPMs), inherently rendering a thermodynamic process. Our primary motivation is to leverage the rich toolbox of thermodynamics…

Machine Learning · Computer Science 2024-01-31 Shervin Sadat Parsi

Learning systems acquire structured internal representations from data, yet classical information-theoretic results state that deterministic transformations do not increase information. This raises a fundamental question: how can learning…

Machine Learning · Computer Science 2026-01-29 Daisuke Okanohara

We consider the thermodynamic properties of systems in contact with an information source and focus on the consequences of energetic cost associated with the exchange of information. To this end we introduce the model of a thermal tape and…

Statistical Mechanics · Physics 2015-06-18 Johannes Hoppenau , Andreas Engel

Biological systems have to build models from their sensory data that allow them to efficiently process previously unseen inputs. Here, we study a neural network learning a linearly separable rule using examples provided by a teacher. We…

Statistical Mechanics · Physics 2017-11-22 Sebastian Goldt , Udo Seifert

Using information theory we derive a thermodynamics for systems evolving under a collective motion, i.e. under a time-odd constraint. An illustration within the Lattice gas Model is given for two model cases: a collision between two complex…

Nuclear Theory · Physics 2015-06-26 F. Gulminelli , PH. Chomaz

We establish universal relations between pattern formation and dissipation with a geometric approach to nonequilibrium thermodynamics of deterministic reaction-diffusion systems. We first provide a way to systematically decompose the…

Statistical Mechanics · Physics 2026-05-04 Ryuna Nagayama , Kohei Yoshimura , Artemy Kolchinsky , Sosuke Ito

In the Internet of Things, learning is one of most prominent tasks. In this paper, we consider an Internet of Things scenario where federated learning is used with simultaneous transmission of model data and wireless power. We investigate…

Signal Processing · Electrical Eng. & Systems 2021-07-22 José Mairton B. da Silva , Konstantinos Ntougias , Ioannis Krikidis , Gábor Fodor , Carlo Fischione

Adaptive physical and biological systems continually process fluctuating information from their environments. When the environment is nonstationary, inference itself becomes a nonequilibrium process with thermodynamic cost. We analyse a…

Statistical Mechanics · Physics 2026-03-23 Aditya Gupta

In this work, we investigate the relation between the concept of ``information rate'', an information geometric method for measuring the speed of the time evolution of the statistical states of a stochastic process, and stochastic…

Statistical Mechanics · Physics 2023-03-29 Adrian-Josue Guel-Cortez , Eun-jin Kim

Adaptive systems -- such as a biological organism gaining survival advantage, an autonomous robot executing a functional task, or a motor protein transporting intracellular nutrients -- must model the regularities and stochasticity in their…

Statistical Mechanics · Physics 2021-04-13 A. B. Boyd , J. P. Crutchfield , M. Gu

In thermal environments, information processing requires thermodynamic costs determined by the second law of thermodynamics. Information processing within finite time is particularly important, since fast information processing has…

Statistical Mechanics · Physics 2024-11-14 Takuya Kamijima , Ken Funo , Takahiro Sagawa

We study the thermodynamic properties induced by non-reciprocal interactions between stochastic degrees of freedom in time- and space-continuous systems. We show that, under fairly general conditions, non-reciprocal coupling alone implies a…

Statistical Mechanics · Physics 2021-04-29 Sarah A. M. Loos , Sabine H. L. Klapp

We provide a unified thermodynamic formalism describing information transfers in autonomous as well as nonautonomous systems described by stochastic thermodynamics. We demonstrate how information is continuously generated in an auxiliary…

Statistical Mechanics · Physics 2014-08-06 Jordan M. Horowitz , Massimiliano Esposito

Recent experiments have indicated that many biological systems self-organise near their critical point, which hints at a common design principle. While it has been suggested that information transmission is optimized near the critical…

Statistical Mechanics · Physics 2021-02-03 Matthijs Meijers , Sosuke Ito , Pieter Rein ten Wolde

An information-theoretic framework is introduced to analyze last-layer embedding, focusing on learned representations for regression tasks. We define representation-rate and derive limits on the reliability with which input-output…

Information Theory · Computer Science 2026-05-27 Deborah Pereg , Michael Wand

Information is instrumental in our understanding of thermodynamics. Their interplay has been studied through completely degenerate Hamiltonians whereby the informational contributions to thermodynamic transformations can be isolated. In…

Quantum Physics · Physics 2024-04-10 Benjamin Stratton , Chung-Yun Hsieh , Paul Skrzypczyk

This paper proposes a novel perspective on learning, positing it as the pursuit of dynamical invariants -- data combinations that remain constant or exhibit minimal change over time as a system evolves. This concept is underpinned by both…

Artificial Intelligence · Computer Science 2024-01-22 Alex Ushveridze

We show that the mutual information between the representation of a learning machine and the hidden features that it extracts from data is bounded from below by the relevance, which is the entropy of the model's energy distribution. Models…

Data Analysis, Statistics and Probability · Physics 2021-01-28 O Duranthon , M Marsili , R Xie