English
Related papers

Related papers: Knowledge as a Breaking of Ergodicity

200 papers

We use a formal correspondence between thermodynamics and inference, where the number of samples can be thought of as the inverse temperature, to study a quantity called ``learning capacity'' which is a measure of the effective…

Machine Learning · Computer Science 2024-10-22 Daiwei Chen , Wei-Kai Chang , Pratik Chaudhari

At low temperatures the configurational phase space of a macroscopic complex system (e.g., a spin-glass) of $N\sim 10^{23}$ interacting particles may split into an exponential number $\Omega_s \sim \exp({\rm const} \times N)$ of ergodic…

Disordered Systems and Neural Networks · Physics 2018-02-14 Haijun Zhou , Kang Li

The behavior of lattice models in which time reversibility is enforced at the level of trajectories (microscopic reversibility) is studied analytically. Conditions for ergodicity breaking are explored, and a few examples of systems…

Statistical Mechanics · Physics 2025-02-17 Piero Olla

We investigate one-dimensional driven diffusive systems where particles may also be created and annihilated in the bulk with sufficiently small rate. In an open geometry, i.e., coupled to particle reservoirs at the two ends, these systems…

Statistical Mechanics · Physics 2007-05-23 A. Rákos , M. Paessens

In the vicinity of a phase transition ergodicity can be broken. Here, different initial many-body configurations evolve towards one of several fixed points, which are macroscopically distinguishable through an order parameter. This…

Quantum Physics · Physics 2025-09-24 Mario Boneberg , Simon Kochsiek , Gabriele Perfetto , Igor Lesanovsky

We study the nature and mechanisms of broken ergodicity (BE) in specific random walk models corresponding to diffusion on random potential surfaces, in both one and high dimension. Using both rigorous results and nonrigorous methods, we…

adap-org · Physics 2008-02-03 D. L. Stein , C. M. Newman

The second law of thermodynamics uses change in free energy of macroscopic systems to set a bound on performed work. Ergotropy plays a similar role in microscopic scenarios, and is defined as the maximum amount of energy that can be…

Quantum Physics · Physics 2022-10-19 Tanmoy Biswas , Marcin Łobejko , Paweł Mazurek , Konrad Jałowiecki , Michał Horodecki

Generative neural networks can produce data samples according to the statistical properties of their training distribution. This feature can be used to test modern computational neuroscience hypotheses suggesting that spontaneous brain…

Neural and Evolutionary Computing · Computer Science 2025-07-29 Lorenzo Tausani , Alberto Testolin , Marco Zorzi

Energy-based learning is a powerful learning paradigm that encapsulates various discriminative and generative approaches. An energy-based model (EBM) is typically formed of inner-model(s) that learn a combination of the different features…

Machine Learning · Computer Science 2023-06-05 Firas Laakom , Jenni Raitoharju , Alexandros Iosifidis , Moncef Gabbouj

We introduce a variant of the asymmetric random average process with continuous state variables where the maximal transport is restricted by a cutoff. For periodic boundary conditions, we show the existence of a phase transition between a…

Statistical Mechanics · Physics 2009-11-07 Frank Zielen , Andreas Schadschneider

How many parameters are required for a model to execute a given task? It has been argued that large language models, pre-trained via self-supervised learning, exhibit emergent capabilities such as multi-step reasoning as their number of…

Machine Learning · Computer Science 2024-09-23 Ingvar Ziemann , Nikolai Matni , George J. Pappas

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

RNA function crucially depends on its structure. Thermodynamic models currently used for secondary structure prediction rely on computing the partition function of folding ensembles, and can thus estimate minimum free-energy structures and…

Biomolecules · Quantitative Biology 2022-07-26 Nicola Calonaci , Alisha Jones , Francesca Cuturello , Michael Sattler , Giovanni Bussi

The potential benefits of model-free reinforcement learning to real robotics systems are limited by its uninformed exploration that leads to slow convergence, lack of data-efficiency, and unnecessary interactions with the environment. To…

Robotics · Computer Science 2020-11-04 Yuchen Wu , Melissa Mozifian , Florian Shkurti

A unified thermodynamic formalism describing the efficiency of learning is proposed. First, we derive an inequality, which is more strength than Clausius's inequality, revealing the lower bound of the entropy-production rate of a subsystem.…

Statistical Mechanics · Physics 2025-04-15 Shanhe Su , Ousi Pan , Shihao Xia , Jincan Chen , Chikako Uchiyama

A thermodynamic formalism describing the efficiency of information learning is proposed, which is applicable for stochastic thermodynamic systems with multiple internal degree of freedom. The learning rate, entropy production rate (EPR),…

Statistical Mechanics · Physics 2023-05-31 Minghao Li , Shihao Xia , Youlin Wang , Minglong Lv , Shanhe Su

Thermodynamics teaches that if a system initially off-equilibrium is coupled to work sources, the maximum work that it may yield is governed by its energy and entropy. For finite systems this bound is usually not reachable. The maximum…

Statistical Mechanics · Physics 2009-11-10 A. E. Allahverdyan , R. Balian , Th. M. Nieuwenhuizen

We present a differentiable formalism for learning free energies that is capable of capturing arbitrarily complex model dependencies on coarse-grained coordinates and finite-temperature response to variation of general system parameters.…

Computational Physics · Physics 2024-05-31 Blake R. Duschatko , Xiang Fu , Cameron Owen , Yu Xie , Albert Musaelian , Tommi Jaakkola , Boris Kozinsky

From a dynamical viewpoint, basic phase transitions of statistical mechanics can be regarded as a breaking of ergodicity. While many random models exhibiting such transitions at the thermodynamics limit exist, finite-dimensional examples…

Mathematical Physics · Physics 2019-09-25 Bastien Fernandez

In many real-world situations, there are constraints on the ways in which a physical system can be manipulated. We investigate the entropy production (EP) and extractable work involved in bringing a system from some initial distribution $p$…

Statistical Mechanics · Physics 2022-11-22 Artemy Kolchinsky , David H. Wolpert
‹ Prev 1 2 3 10 Next ›