English
Related papers

Related papers: Stochastic weight matrix dynamics during learning …

200 papers

We propose to optimize neural networks with a uniformly-distributed random learning rate. The associated stochastic gradient descent algorithm can be approximated by continuous stochastic equations and analyzed within the Fokker-Planck…

Machine Learning · Computer Science 2020-10-13 Daniele Musso

Uncertainties are abundant in complex systems. Mathematical models for these systems thus contain random effects or noises. The models are often in the form of stochastic differential equations, with some parameters to be determined by…

Numerical Analysis · Mathematics 2015-03-13 Jiarui Yang , Jinqiao Duan

We consider stochastic dynamics of a particle on a plane in presence of two noises and a confining parabolic potential - an analog of the experimentally-relevant Brownian Gyrator (BG) model. In contrast to the standard BG model, we suppose…

Statistical Mechanics · Physics 2025-12-16 Timothée Herbeau , Leonid Pastur , Pascal Viot , Gleb Oshanin

Stochastic inverse problems considered in this article consist of estimating the probability distributions of intrinsically random inputs of computer models. These estimations are based on observable outputs affected by model noise, and…

Statistics Theory · Mathematics 2025-03-17 Nicolas Bousquet , Mélanie Blazère , Thomas Cerbelaud

In this paper we study binary interaction schemes with uncertain parameters for a general class of Boltzmann-type equations with applications in classical gas and aggregation dynamics. We consider deterministic (i.e., a priori averaged) and…

Analysis of PDEs · Mathematics 2018-11-05 Andrea Tosin , Mattia Zanella

We study a generalization of the Brownian bridge as a stochastic process that models the position and velocity of inertial particles between the two end-points of a time interval. The particles experience random acceleration and are assumed…

Systems and Control · Computer Science 2014-07-15 Yongxin Chen , Tryphon Georgiou

Training neural networks with batch normalization and weight decay has become a common practice in recent years. In this work, we show that their combined use may result in a surprising periodic behavior of optimization dynamics: the…

Machine Learning · Computer Science 2022-01-19 Ekaterina Lobacheva , Maxim Kodryan , Nadezhda Chirkova , Andrey Malinin , Dmitry Vetrov

We introduce a deductive statistical mechanics approach for granular materials which is formally built from few realistic physical assumptions. The main finding is an universal behavior for the distribution of the density fluctuations. Such…

Soft Condensed Matter · Physics 2008-06-25 T. Aste , T. Di Matteo

We study the dynamics of a Brownian motion with a diffusion coefficient which evolves stochastically. We first study this process in arbitrary dimensions and find the scaling form and the corresponding scaling function of the position…

Statistical Mechanics · Physics 2023-01-30 Ion Santra , Urna Basu , Sanjib Sabhapandit

We present a Bayesian non-parametric way of inferring stochastic differential equations for both regression tasks and continuous-time dynamical modelling. The work has high emphasis on the stochastic part of the differential equation, also…

Machine Learning · Statistics 2020-06-29 Martin Jørgensen , Marc Peter Deisenroth , Hugh Salimbeni

We study the universality of spectral statistics of large random matrices. We consider $N\times N$ symmetric, hermitian or quaternion self-dual random matrices with independent, identically distributed entries (Wigner matrices) where the…

Mathematical Physics · Physics 2015-05-18 Laszlo Erdos

We prove that the local eigenvalue statistics of real symmetric Wigner-type matrices near the cusp points of the eigenvalue density are universal. Together with the companion paper [arXiv:1809.03971], which proves the same result for the…

Probability · Mathematics 2019-10-23 Giorgio Cipolloni , László Erdős , Torben Krüger , Dominik Schröder

We analyze the dynamics of an algorithm for approximate inference with large Gaussian latent variable models in a student-teacher scenario. To model nontrivial dependencies between the latent variables, we assume random covariance matrices…

Machine Learning · Computer Science 2020-08-26 Burak Çakmak , Manfred Opper

We study a distributed learning process observed in human groups and other social animals. This learning process appears in settings in which each individual in a group is trying to decide over time, in a distributed manner, which option to…

Machine Learning · Computer Science 2017-05-10 L. Elisa Celis , Peter M. Krafft , Nisheeth K. Vishnoi

We study the problem of learning latent variables in Gaussian graphical models. Existing methods for this problem assume that the precision matrix of the observed variables is the superposition of a sparse and a low-rank component. In this…

Machine Learning · Statistics 2017-07-12 Mohammadreza Soltani , Chinmay Hegde

We consider a neural network with adapting synapses whose dynamics can be analitically computed. The model is made of $N$ neurons and each of them is connected to $K$ input neurons chosen at random in the network. The synapses are…

Disordered Systems and Neural Networks · Physics 2009-10-30 G. Lattanzi , G. Nardulli , G. Pasquariello , S. Stramaglia

Combining insights from machine learning and quantum Monte Carlo, the stochastic reconfiguration method with neural network Ansatz states is a promising new direction for high-precision ground state estimation of quantum many-body problems.…

Quantum Physics · Physics 2020-10-14 Chae-Yeun Park , Michael J. Kastoryano

Despite the success of fractional Brownian motion (fBm) in modeling systems that exhibit anomalous diffusion due to temporal correlations, recent experimental and theoretical studies highlight the necessity for a more comprehensive approach…

Statistical Mechanics · Physics 2024-07-02 Adrian Pacheco-Pozo , Diego Krapf

The Boltzmann machine provides a useful framework to learn highly complex, multimodal and multiscale data distributions that occur in the real world. The default method to learn its parameters consists of minimizing the Kullback-Leibler…

Machine Learning · Statistics 2015-07-09 Grégoire Montavon , Klaus-Robert Müller , Marco Cuturi

At the macroscopic scale, many important models of collective motion fall into the class of kinematic flows for which both velocity and diffusion terms depend only on particle density. When total particle numbers are fixed and finite,…

Adaptation and Self-Organizing Systems · Physics 2022-04-12 Jeremy Worsfold , Tim Rogers , Paul Milewski