English
Related papers

Related papers: A note on the dynamics of extended-context disorde…

200 papers

Modeling the world can benefit robot learning by providing a rich training signal for shaping an agent's latent state space. However, learning world models in unconstrained environments over high-dimensional observation spaces such as…

Machine Learning · Computer Science 2021-12-03 Nitish Srivastava , Walter Talbott , Martin Bertran Lopez , Shuangfei Zhai , Josh Susskind

The mean number <N> of metastable states in higher order short-range spin glasses is estimated analytically using a variational method introduced by Tanaka and Edwards for very large coordination numbers. For lattices with small…

Statistical Mechanics · Physics 2009-10-31 Viviane M. de Oliveira , J. F. Fontanari , Peter F. Stadler

Recently, recurrent models such as state space models and linear attention have become popular due to their linear complexity in the sequence length. Thanks to their recurrent nature, in principle they can process arbitrarily long…

Machine Learning · Computer Science 2025-10-14 Ricardo Buitrago Ruiz , Albert Gu

We propose an approach for improving sequence modeling based on autoregressive normalizing flows. Each autoregressive transform, acting across time, serves as a moving frame of reference, removing temporal correlations, and simplifying the…

Machine Learning · Computer Science 2022-03-09 Joseph Marino , Lei Chen , Jiawei He , Stephan Mandt

Transformer LMs show emergent reasoning that resists mechanistic understanding. We offer a statistical physics framework for continuous-time chain-of-thought reasoning dynamics. We model sentence-level hidden state trajectories as a…

Artificial Intelligence · Computer Science 2025-06-06 Jack David Carson , Amir Reisizadeh

Diverse equilibrium systems with heterogeneous interactions lie at the edge of stability. Such marginally stable states are dynamically selected as the most abundant ones or as those with the largest basins of attraction. On the other hand,…

Disordered Systems and Neural Networks · Physics 2025-10-10 Carles Martorell , Rubén Calvo , Alessia Annibale , Miguel A. Muñoz

Driven Langevin processes have appeared in a variety of fields due to the relevance of natural phenomena having both deterministic and stochastic effects. The stochastic currents and fluxes in these systems provide a convenient set of…

Chemical Physics · Physics 2017-01-04 Michael J. Catanzaro , Vladimir Y. Chernyak , John R. Klein

This paper shows that a large class of fading memory state-space systems driven by discrete-time observations of dynamical systems defined on compact manifolds always yields continuously differentiable synchronizations. This general result…

Dynamical Systems · Mathematics 2021-06-09 Lyudmila Grigoryeva , Allen Hart , Juan-Pablo Ortega

Kinetically constrained models (KCMs) are interacting particle systems introduced in the '80s by physicists to have accessible stochastic models with glassy-type dynamics. The key mechanism behind the complex evolution of these otherwise…

Probability · Mathematics 2025-10-24 Fabio Martinelli , Assaf Shapira , Cristina Toninelli

Autoregressive (AR) models have become a popular tool for unsupervised learning, achieving state-of-the-art log likelihood estimates. We investigate the use of AR models as density estimators in two settings -- as a learning signal for…

Machine Learning · Computer Science 2019-10-18 Murtaza Dalal , Alexander C. Li , Rohan Taori

In social science, formal and quantitative models, such as ones describing economic growth and collective action, are used to formulate mechanistic explanations, provide predictions, and uncover questions about observed phenomena. Here, we…

Symbolic Computation · Computer Science 2023-08-17 Julia Balla , Sihao Huang , Owen Dugan , Rumen Dangovski , Marin Soljacic

We study the dynamical behavior of a lattice model of glass former on a random graph, where no corrections to the mean field description are expected. We find that the behavior of dynamical correlation functions and dynamical susceptibility…

Disordered Systems and Neural Networks · Physics 2011-06-17 A. de Candia , M. Mauro , A. Coniglio

We introduce and analytically study a generalized p-spin glass like model that captures some of the main features of attractive glasses, recently found by Mode Coupling investigations, such as a glass/glass transition line and dynamical…

Statistical Mechanics · Physics 2009-11-10 Antonio Caiazzo , Antonio Coniglio , Mario Nicodemi

Investigating the emergence of complexity in disordered interacting systems, central to fields like spin glass physics, remains challenging due to difficulties in systematic experimental tuning. We introduce a tunable artificial spin…

Mesoscale and Nanoscale Physics · Physics 2025-06-10 Vinayak Shantaram Bhat , M. Benjamin Jungfleisch

Glassy systems reveal a wide variety of generic behaviors, which lack a unified theoretical description. Here, we study a mean-field model, recently shown to reproduce the universal non-phononic vibrational spectra of glasses, under…

Disordered Systems and Neural Networks · Physics 2025-12-19 Makoto Suda , Edan Lerner , Eran Bouchbinder

We introduce generative models for accelerating simulations of complex systems through learning and evolving their effective dynamics. In the proposed Generative Learning of Effective Dynamics (G-LED), instances of high dimensional data are…

Machine Learning · Computer Science 2024-02-28 Han Gao , Sebastian Kaltenbach , Petros Koumoutsakos

We propose a probabilistic framework for developing computational models of biological neural systems. In this framework, physiological recordings are viewed as discrete-time partial observations of an underlying continuous-time stochastic…

Neurons and Cognition · Quantitative Biology 2026-02-10 Ahmed ElGazzar , Marcel van Gerven

These lecture notes focus on the mean field theory of spin glasses, with particular emphasis on the presence of a very large number of metastable states in these systems. This phenomenon, and some of its physical consequences, will be…

Statistical Mechanics · Physics 2014-09-23 Francesco Zamponi

This paper considers a class of reinforcement-based learning (namely, perturbed learning automata) and provides a stochastic-stability analysis in repeatedly-played, positive-utility, finite strategic-form games. Prior work in this class of…

Computer Science and Game Theory · Computer Science 2019-01-29 Georgios C. Chasparis

Recently, generative machine-learning models have gained popularity in physics, driven by the goal of improving the efficiency of Markov chain Monte Carlo techniques and of exploring their potential in capturing experimental data…

Statistical Mechanics · Physics 2021-09-03 Japneet Singh , Vipul Arora , Vinay Gupta , Mathias S. Scheurer