English
Related papers

Related papers: Stochastic weight matrix dynamics during learning …

200 papers

This paper analyzes the convergence and generalization of training a one-hidden-layer neural network when the input features follow the Gaussian mixture model consisting of a finite number of Gaussian distributions. Assuming the labels are…

Machine Learning · Computer Science 2023-01-30 Hongkang Li , Shuai Zhang , Meng Wang

We study the problem of learning mixtures of $k$ Gaussians in $d$ dimensions. We make no separation assumptions on the underlying mixture components: we only require that the covariance matrices have bounded condition number and that the…

Data Structures and Algorithms · Computer Science 2024-11-20 Sitan Chen , Vasilis Kontonis , Kulin Shah

Efficiently learning mixture of Gaussians is a fundamental problem in statistics and learning theory. Given samples coming from a random one out of k Gaussian distributions in Rn, the learning problem asks to estimate the means and the…

Machine Learning · Computer Science 2015-03-11 Rong Ge , Qingqing Huang , Sham M. Kakade

We define a new diffusive matrix model converging towards the $\beta$ -Dyson Brownian motion for all $\beta\in [0,2]$ that provides an explicit construction of $\beta$-ensembles of random matrices that is invariant under the…

Probability · Mathematics 2013-01-29 Romain Allez , Jean-Philippe Bouchaud , Alice Guionnet

We introduce a new class of continuous-time models of the stochastic volatility of asset prices. The models can simultaneously incorporate roughness and slowly decaying autocorrelations, including proper long memory, which are two stylized…

Statistical Finance · Quantitative Finance 2021-01-06 Mikkel Bennedsen , Asger Lunde , Mikko S. Pakkanen

We consider the classical dynamics of bosonic and fermionic matrix variables in complex Hilbert space, defined by a trace action, assuming cyclic invariance under the trace and the presence of a global unitary invariance. With plausible and…

High Energy Physics - Theory · Physics 2007-05-23 Stephen L. Adler

A restricted Boltzmann machine is a generative probabilistic graphic network. A probability of finding the network in a certain configuration is given by the Boltzmann distribution. Given training data, its learning is done by optimizing…

Disordered Systems and Neural Networks · Physics 2020-05-28 Sangchul Oh , Abdelkader Baggag , Hyunchul Nha

We consider $N\times N$ symmetric or hermitian random matrices with independent, identically distributed entries where the probability distribution for each matrix element is given by a measure $\nu$ with a subexponential decay. We prove…

Mathematical Physics · Physics 2017-08-23 Laszlo Erdos

Recent result of the numerical simulation of stochastic motion of conservative mechanical or weakly damped Brownian motion subject to conservative forces reveals that, in the case of Gaussian random forces, the path probability depends…

Statistical Mechanics · Physics 2011-11-08 Qiuping A. Wang

A study of the non-dissipative Brownian motion in vacuum is presented. The noise source associated to the stochastic process assumed in this work is vacuum fluctuations of some quantum field capable of interact with a massive particle. For…

Classical Physics · Physics 2007-05-23 J. M. A. Figueiredo

Macroscopic dynamical descriptions of complex physical systems are crucial for understanding and controlling material behavior. With the growing availability of data and compute, machine learning has become a promising alternative to…

Computational Physics · Physics 2026-03-24 Mengyi Chen , Pengru Huang , Kostya S. Novoselov , Qianxiao Li

In this paper, we study a stochastic parabolic problem involving a nonlocal diffusion operator associated with nonlocal Robin-type boundary conditions. The stochastic dynamics under consideration are driven by a mixture of a classical…

The horizontal dynamics of a bouncing ball interacting with an irregular surface is investigated and is found to demonstrate behavior analogous to a random walk. Its stochastic character is substantiated by the calculation of a permutation…

Physics Education · Physics 2025-09-15 Luiz Antonio Barreiro

We consider $N\times N$ Hermitian Wigner random matrices $H$ where the probability density for each matrix element is given by the density $\nu(x)= e^{- U(x)}$. We prove that the eigenvalue statistics in the bulk is given by Dyson sine…

Mathematical Physics · Physics 2009-10-21 Laszlo Erdos , Sandrine Peche , Jose A. Ramirez , Benjamin Schlein , Horng-Tzer Yau

We describe the idea of studying quantum gravity by means of dynamical triangulations and give examples of its implementation in 2, 3 and 4 space time dimensions. For $d=2$ we consider the generic hermitian 1-matrix model. We introduce the…

High Energy Physics - Theory · Physics 2007-05-23 C. F. Kristjansen

We present a theory for the dynamical evolution of a quantum system coupled to a complex many-body intrinsic system/environment. By modelling the intrinsic many-body system with parametric random matrices, we study the types of effective…

Nuclear Theory · Physics 2009-10-30 Aurel Bulgac , Gui DoDang , Dimitri Kusnezov

Dynamic Boltzmann Machine (DyBM) has been shown highly efficient to predict time-series data. Gaussian DyBM is a DyBM that assumes the predicted data is generated by a Gaussian distribution whose first-order moment (mean) dynamically…

Machine Learning · Statistics 2017-12-19 Rudy Raymond , Takayuki Osogami , Sakyasingha Dasgupta

We provide an overview of high dimensional dynamical systems driven by random matrices, focusing on applications to simple models of learning and generalization in machine learning theory. Using both cavity method arguments and path…

Disordered Systems and Neural Networks · Physics 2026-01-12 Blake Bordelon , Cengiz Pehlevan

Machine learning provides algorithms that can learn from data and make inferences or predictions on data. Stochastic acceptors or probabilistic automata are stochastic automata without output that can model components in machine learning…

Machine Learning · Computer Science 2018-12-27 Karl-Heinz Zimmermann

Learning is based on synaptic plasticity, which affects and is driven by neural activity. Because pre- and postsynaptic spiking activity is shaped by randomness, the synaptic weights follow a stochastic process, requiring a probabilistic…

Neurons and Cognition · Quantitative Biology 2026-01-14 Jakob Stubenrauch , Naomi Auer , Richard Kempter , Benjamin Lindner
‹ Prev 1 4 5 6 7 8 10 Next ›