English
Related papers

Related papers: A Dynamical Mean-Field Theory for Learning in Rest…

200 papers

Efficient sampling of the Boltzmann distribution of molecular systems is a long-standing challenge. Recently, instead of generating long molecular dynamics simulations, generative machine learning methods such as normalizing flows have been…

Machine Learning · Computer Science 2024-08-06 Henrik Schopmans , Pascal Friederich

Stable dynamical systems are a flexible tool to plan robotic motions in real-time. In the robotic literature, dynamical system motions are typically planned without considering possible limitations in the robot's workspace. This work…

Robotics · Computer Science 2020-03-26 Matteo Saveriano , Dongheui Lee

Multiscale phenomena which include several processes occuring simultaneously at different length scales and exchanging energy with each other, are widespread in magnetism. These phenomena often govern the magnetization reversal dynamics,…

Materials Science · Physics 2009-10-31 V. V. Dobrovitski , M. I. Katsnelson , B. N. Harmon

We consider distributed estimation of the inverse covariance matrix, also called the concentration or precision matrix, in Gaussian graphical models. Traditional centralized estimation often requires global inference of the covariance…

Machine Learning · Statistics 2015-06-15 Zhaoshi Meng , Dennis Wei , Ami Wiesel , Alfred O. Hero

We study barrier crossing in a two-state system, namely the kinetic Ising model, in the presence of a weak bias field and spatially homogeneous, but time-dependent, Gaussian random fields. We find that the bias field determines the location…

Statistical Mechanics · Physics 2026-05-28 Sara Oliver-Bonafoux , Raúl Toral , Amitabha Chakrabarti

Random matrix theory of the transition strengths is applied to transport in the strongly localized regime. The crossover distribution function between the different ensembles is derived and used to predict quantitatively the {\sl universal}…

Condensed Matter · Physics 2009-10-22 Y. Meir , O. Entin-Wohlman

We consider restricted Boltzmann machines with a binary visible layer and a Gaussian hidden layer trained by an unlabelled dataset composed of noisy realizations of a single ground pattern. We develop a statistical mechanics framework to…

Disordered Systems and Neural Networks · Physics 2024-06-17 Alberto Fachechi , Elena Agliari , Miriam Aquaro , Anthony Coolen , Menno Mulder

There are many advantages to use probability method for nonlinear system identification, such as the noises and outliers in the data set do not affect the probability models significantly; the input features can be extracted in probability…

Systems and Control · Computer Science 2018-06-08 Erick de la Rosa , Wen Yu

Generalization is one of the most important issues in machine learning problems. In this study, we consider generalization in restricted Boltzmann machines (RBMs). We propose an RBM with multivalued hidden variables, which is a simple…

Machine Learning · Statistics 2020-01-09 Yuuki Yokoyama , Tomu Katsumata , Muneki Yasuda

This paper presents a novel method that allows a machine learning algorithm following the transformation-based learning paradigm \cite{brill95:tagging} to be applied to multiple classification tasks by training jointly and simultaneously on…

Computation and Language · Computer Science 2007-05-23 Radu Florian , Grace Ngai

We describe a dynamic programming algorithm for computing the marginal distribution of discrete probabilistic programs. This algorithm takes a functional interpreter for an arbitrary probabilistic programming language and turns it into an…

Artificial Intelligence · Computer Science 2012-09-12 Andreas Stuhlmüller , Noah D. Goodman

We implement the Ising model on a structural connectivity matrix describing the brain at a coarse scale. Tuning the model temperature to its critical value, i.e. at the susceptibility peak, we find a maximal amount of total information…

Neurons and Cognition · Quantitative Biology 2013-09-03 Daniele Marinazzo , Mario Pellicoro , Guorong Wu , Leonardo Angelini , Jesus M Cortes , Sebastiano Stramaglia

Restricted Boltzmann Machines are key tools in Machine Learning and are described by the energy function of bipartite spin-glasses. From a statistical mechanical perspective, they share the same Gibbs measure of Hopfield networks for…

Mathematical Physics · Physics 2017-08-02 Elena Agliari , Adriano Barra , Chiara Longo , Daniele Tantari

We review Boltzmann machines and energy-based models. A Boltzmann machine defines a probability distribution over binary-valued patterns. One can learn parameters of a Boltzmann machine via gradient based approaches in a way that log…

Neural and Evolutionary Computing · Computer Science 2019-01-21 Takayuki Osogami

Revealing hidden features in unlabeled data is called unsupervised feature learning, which plays an important role in pretraining a deep neural network. Here we provide a statistical mechanics analysis of the unsupervised learning in a…

Machine Learning · Computer Science 2017-05-16 Haiping Huang

In this paper we introduce and discuss kinetic equations for the evolution of the probability distribution of the number of particles in a population subject to binary interactions. The microscopic binary law of interaction is assumed to be…

Probability · Mathematics 2015-01-13 Federico Bassetti , Giuseppe Toscani

Bilinear dynamical systems are ubiquitous in many different domains and they can also be used to approximate more general control-affine systems. This motivates the problem of learning bilinear systems from a single trajectory of the…

Machine Learning · Computer Science 2022-08-31 Yahya Sattar , Samet Oymak , Necmiye Ozay

Using an effective Hamiltonian including the Zeeman and internal interactions, we describe the quantum theory of magnetization dynamics when the spin system evolves non-adiabatically and out of equilibrium. The Lewis-Riesenfeld dynamical…

Other Condensed Matter · Physics 2008-11-26 F. M. Saradzhev , F. C. Khanna , Sang Pyo Kim , M. de Montigny

Near-term noisy intermediate-scale quantum circuits can efficiently implement implicit probabilistic models in discrete spaces, supporting distributions that are practically infeasible to sample from using classical means. One of the…

Quantum Physics · Physics 2022-04-07 Ivana Nikoloska , Osvaldo Simeone

The restricted Boltzmann machine (RBM) is a flexible tool for modeling complex data, however there have been significant computational difficulties in using RBMs to model high-dimensional multinomial observations. In natural language…

Machine Learning · Computer Science 2012-07-06 George E. Dahl , Ryan P. Adams , Hugo Larochelle