English
Related papers

Related papers: Stochastic weight matrix dynamics during learning …

200 papers

Deep kernel learning combines the non-parametric flexibility of kernel methods with the inductive biases of deep learning architectures. We propose a novel deep kernel learning model and stochastic variational inference procedure which…

Machine Learning · Statistics 2016-11-03 Andrew Gordon Wilson , Zhiting Hu , Ruslan Salakhutdinov , Eric P. Xing

This paper studies continuous-time stochastic control problems whose controlled states are fully non-Markovian and depend on unknown model parameters. Such problems arise naturally in path-dependent stochastic differential equations,…

Machine Learning · Statistics 2026-05-29 Dorival Leão , Alberto Ohashi , Simone Scotti , Adolfo M. D da Silva

As the size of modern data sets exceeds the disk and memory capacities of a single computer, machine learning practitioners have resorted to parallel and distributed computing. Given that optimization is one of the pillars of machine…

Machine Learning · Statistics 2019-12-10 Biyi Fang , Diego Klabjan

We provide an algorithm based on weighted-ensemble (WE) methods, to accurately sample systems at steady state. Applying our method to different one- and two-dimensional models, we succeed to calculate steady state probabilities of order…

Statistical Mechanics · Physics 2015-06-15 Justus A. Kromer , Lutz Schimansky-Geier , Raul Toral

Given a segment of time series of a system at a particular set of parameter values, can one infers the global behavior of the system in its parameter space? Here we show that by using a learning machine we can achieve such a goal to a…

Adaptation and Self-Organizing Systems · Physics 2022-04-15 Hong Zhao

The Wigner-Gaudin-Mehta-Dyson conjecture asserts that the local eigenvalue statistics of large random matrices exhibit universal behavior depending only on the symmetry class of the matrix ensemble. For invariant matrix models, the…

Probability · Mathematics 2012-01-31 Laszlo Erdos , Horng-Tzer Yau

We look at the equilibrium of a Brownian particle in an inhomogeneous space following the alternative approach proposed in ref.[1]. We consider a coordinate dependent damping that makes the stochastic dynamics the one with multiplicative…

Statistical Mechanics · Physics 2014-10-07 Avik Biswas , A. Bhattacharyay

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

Graphical models are powerful tools for modeling high-dimensional data, but learning graphical models in the presence of latent variables is well-known to be difficult. In this work we give new results for learning Restricted Boltzmann…

Machine Learning · Computer Science 2020-07-28 Surbhi Goel , Adam Klivans , Frederic Koehler

Stochastic gradient descent plays a fundamental role in nearly all applications of deep learning. However its ability to converge to a global minimum remains shrouded in mystery. In this paper we propose to study the behavior of the loss…

Machine Learning · Computer Science 2023-02-02 Mark Sandler , Andrey Zhmoginov , Max Vladymyrov , Nolan Miller

We discuss the geometric foundation behind the use of stochastic processes in the frame bundle of a smooth manifold to build stochastic models with applications in statistical analysis of non-linear data. The transition densities for the…

Differential Geometry · Mathematics 2016-08-29 Stefan Sommer , Anne Marie Svane

We study the problem of system identification for stochastic continuous-time dynamics, based on a single finite-length state trajectory. We present a method for estimating the possibly unstable open-loop matrix by employing properly…

Machine Learning · Statistics 2025-09-30 Reza Sadeghi Hafshejani , Mohamad Kazem Shirani Fradonbeh

We develop and analyze a broad family of stochastic/randomized algorithms for inverting a matrix. We also develop specialized variants maintaining symmetry or positive definiteness of the iterates. All methods in the family converge…

Numerical Analysis · Mathematics 2016-03-24 Robert M. Gower , Peter Richtárik

We present a learning theory for the training of a linear system operator having an input compositional variable and propose a Bayesian inversion method for inferring the unknown variable from an output of a noisy linear system. We assume…

Machine Learning · Statistics 2018-07-03 Se Un Park

We prove the Wigner-Dyson-Mehta conjecture at fixed energy in the bulk of the spectrum for generalized symmetric and Hermitian Wigner matrices. Previous results concerning the universality of random matrices either require an averaging in…

Probability · Mathematics 2015-04-17 Paul Bourgade , Laszlo Erdos , Hong-Tzer Yau , Jun Yin

The circular Dyson Brownian motion model refers to the stochastic dynamics of the log-gas on a circle. It also specifies the eigenvalues of certain parameter-dependent ensembles of unitary random matrices. This model is considered with the…

Statistical Mechanics · Physics 2016-08-31 P. J. Forrester , T. Nagao

The asymptotic behavior of the stochastic gradient algorithm with a biased gradient estimator is analyzed. Relying on arguments based on the dynamic system theory (chain-recurrence) and the differential geometry (Yomdin theorem and…

Statistics Theory · Mathematics 2017-09-04 Vladislav B. Tadic , Arnaud Doucet

One century after Einstein's work, Brownian Motion still remains both a fundamental open issue and a continous source of inspiration for many areas of natural sciences. We first present a discussion about stochastic and deterministic…

Chaotic Dynamics · Physics 2009-11-10 Fabio Cecconi , Massimo Cencini , Massimo Falcioni , Angelo Vulpiani

We consider a general Langevin dynamics for the one-dimensional N-particle Coulomb gas with confining potential $V$ at temperature $\beta$. These dynamics describe for $\beta=2$ the time evolution of the eigenvalues of $N\times N$ random…

Mathematical Physics · Physics 2016-04-04 Jeremie Unterberger

Recent work has established an empirically successful framework for adapting learning rates for stochastic gradient descent (SGD). This effectively removes all needs for tuning, while automatically reducing learning rates over time on…

Machine Learning · Computer Science 2013-03-28 Tom Schaul , Yann LeCun