English
Related papers

Related papers: Stochastic Thermodynamics of Learning Parametric P…

200 papers

We develop a statistical mechanical interpretation of algorithmic information theory by introducing the notion of thermodynamic quantities, such as free energy, energy, statistical mechanical entropy, and specific heat, into algorithmic…

Information Theory · Computer Science 2009-04-09 Kohtaro Tadaki

We develop a thermodynamic theory for machine learning (ML) systems. Similar to physical thermodynamic systems which are characterized by energy and entropy, ML systems possess these characteristics as well. This comparison inspire us to…

Machine Learning · Computer Science 2024-04-23 Dong Zhang

Information dynamics is an emerging description of information processing in complex systems which describes systems in terms of intrinsic computation, identifying computational primitives of information storage and transfer. In this paper…

Statistical Mechanics · Physics 2018-10-03 Richard E. Spinney , Joseph T. Lizier , Mikhail Prokopenko

In recent years, the unified theory of information and thermodynamics has been intensively discussed in the context of stochastic thermodynamics. The unified theory reveals that information theory would be useful to understand…

Statistical Mechanics · Physics 2018-07-23 Sosuke Ito

This paper provides a perspective on applying the concepts of information thermodynamics, developed recently in non-equilibrium statistical physics, to problems in theoretical neuroscience. Historically, information and energy in…

Neurons and Cognition · Quantitative Biology 2024-09-27 Jan Karbowski

Thermodynamics could be seen as an expression of physics at a high epistemic level. As such, its potential as an inductive bias to help machine learning procedures attain accurate and credible predictions has been recently realized in many…

Machine Learning · Computer Science 2023-05-29 Elias Cueto , Francisco Chinesta

Generalized Probabilistic Theories (GPTs) provide a unified framework for describing probabilistic physical theories, encompassing classical and quantum theories as well as hypothetical theories beyond quantum mechanics. Since most GPTs are…

Quantum Physics · Physics 2026-05-14 Koki Ono , Shun Umekawa , Hiroyasu Tajima

We generalize stochastic thermodynamics to include information reservoirs. Such information reservoirs, which can be modeled as a sequence of bits, modify the second law. For example, work extraction from a system in contact with a single…

Statistical Mechanics · Physics 2014-11-17 Andre C. Barato , Udo Seifert

Virtually every organism gathers information about its noisy environment and builds models from that data, mostly using neural networks. Here, we use stochastic thermodynamics to analyse the learning of a classification rule by a neural…

Statistical Mechanics · Physics 2017-01-31 Sebastian Goldt , Udo Seifert

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

Connections between information theory and thermodynamics have proven to be very useful to establish bounding limits for physical processes. Ideas such as Landauer's erasure principle and information assisted work extraction have greatly…

Quantum Physics · Physics 2013-12-17 Kaonan Micadei , Roberto M. Serra , Lucas C. Celeri

Experimental data bases are typically very large and high dimensional. To learn from them requires to recognize important features (a pattern), often present at scales different to that of the recorded data. Following the experience…

Data Analysis, Statistics and Probability · Physics 2021-01-21 Francisco Chinesta , Elias Cueto , Miroslav Grmela , Beatriz Moya , Michal Pavelka , Martin Sipka

This tutorial investigates the convergence of statistical mechanics and learning theory, elucidating the potential enhancements in machine learning methodologies through the integration of foundational principles from physics. The tutorial…

Machine Learning · Computer Science 2024-11-26 Star , Liu

In this work, we suggest a parameterized statistical model (the gamma distribution) for the frequency of word occurrences in long strings of English text and use this model to build a corresponding thermodynamic picture by constructing the…

Information Theory · Computer Science 2011-03-01 Kostadin Koroutchev , Jian Shen , Elka Koroutcheva , Manuel Cebrian

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

New discoveries in chemistry and materials science, with increasingly expanding volume of requisite knowledge and experimental workload, provide unique opportunities for machine learning (ML) to take critical roles in accelerating research…

The common saying, that information is power, takes a rigorous form in stochastic thermodynamics, where a quantitative equivalence between the two helps explain the paradox of Maxwell's demon in its ability to reduce entropy. In the present…

Statistical Mechanics · Physics 2021-03-09 Amirhossein Taghvaei , Olga Movilla Miangolarra , Rui Fu , Yongxin Chen , Tryphon T. Georgiou

The formalism of state estimation and hidden Markov models (HMMs) can simplify and clarify the discussion of stochastic thermodynamics in the presence of feedback and measurement errors. After reviewing the basic formalism, we use it to…

Statistical Mechanics · Physics 2015-11-13 John Bechhoefer

Information thermodynamics relates the rate of change of mutual information between two interacting subsystems to their thermodynamics when the joined system is described by a bipartite stochastic dynamics satisfying local detailed balance.…

Statistical Mechanics · Physics 2022-08-05 Emanuele Penocchio , Francesco Avanzini , Massimiliano Esposito

We develop inductive biases for the machine learning of complex physical systems based on the port-Hamiltonian formalism. To satisfy by construction the principles of thermodynamics in the learned physics (conservation of energy,…

Machine Learning · Computer Science 2023-03-28 Quercus Hernández , Alberto Badías , Francisco Chinesta , Elías Cueto
‹ Prev 1 2 3 10 Next ›