English
Related papers

Related papers: Random Matrix Theory for Stochastic Gradient Desce…

200 papers

This paper studies the problem of recursively estimating the weighted adjacency matrix of a network out of a temporal sequence of binary-valued observations. The observation sequence is generated from nonlinear networked dynamics in which…

Systems and Control · Electrical Eng. & Systems 2019-12-06 Yu Xing , Xingkang He , Haitao Fang , Karl Henrik Johansson

Stochastic Gradient Descent (SGD) and its variants are almost universally used to train neural networks and to fit a variety of other parametric models. An important hyperparameter in this context is the batch size, which determines how…

Optimization and Control · Mathematics 2023-12-05 Stefan Perko

Stochastic gradient descent samples uniformly the training set to build an unbiased gradient estimate with a limited number of samples. However, at a given step of the training process, some data are more helpful than others to continue…

Machine Learning · Computer Science 2023-03-30 Thibault Lahire

Batch Normalization (BN) has become a cornerstone of deep learning across diverse architectures, appearing to help optimization as well as generalization. While the idea makes intuitive sense, theoretical analysis of its effectiveness has…

Machine Learning · Computer Science 2018-12-11 Sanjeev Arora , Zhiyuan Li , Kaifeng Lyu

This paper is the second of a series devoted to the study of the dynamics of the spectrum of large random matrices. We study general extensions of the partial differential equation arising to characterize the limit spectral measure of the…

Analysis of PDEs · Mathematics 2024-03-20 Charles Bertucci , Jean-Michel Lasry , Pierre Louis Lions

Stochastic gradient methods are the workhorse (algorithms) of large-scale optimization problems in machine learning, signal processing, and other computational sciences and engineering. This paper studies Markov chain gradient descent, a…

Optimization and Control · Mathematics 2018-09-13 Tao Sun , Yuejiao Sun , Wotao Yin

Ensembles of neural network weight matrices are studied through the training process for the MNIST classification problem, testing the efficacy of matrix models for representing their distributions, under assumptions of Gaussianity and…

Machine Learning · Computer Science 2025-10-08 Edward Hirst , Sanjaye Ramgoolam

The algorithms used to train neural networks, like stochastic gradient descent (SGD), have close parallels to natural processes that navigate a high-dimensional parameter space -- for example protein folding or evolution. Our study uses a…

Machine Learning · Computer Science 2023-06-07 Shishir Adhikari , Alkan Kabakçıoğlu , Alexander Strang , Deniz Yuret , Michael Hinczewski

Linear dynamical systems are canonical models for learning-based control of plants with uncertain dynamics. The setting consists of a stochastic differential equation that captures the state evolution of the plant understudy, while the true…

Systems and Control · Electrical Eng. & Systems 2022-01-03 Mohamad Kazem Shirani Faradonbeh , Mohamad Sadegh Shirani Faradonbeh

We define an evolving in-time Bayesian neural network called a Hidden Markov Neural Network, which addresses the crucial challenge in time-series forecasting and continual learning: striking a balance between adapting to new data and…

Machine Learning · Statistics 2025-01-17 Lorenzo Rimella , Nick Whiteley

Unsupervised learning aims at the discovery of hidden structure that drives the observations in the real world. It is essential for success in modern machine learning. Latent variable models are versatile in unsupervised learning and have…

Machine Learning · Computer Science 2016-06-13 Furong Huang

In this paper we study several classes of stochastic optimization algorithms enriched with heavy ball momentum. Among the methods studied are: stochastic gradient descent, stochastic Newton, stochastic proximal point and stochastic dual…

Optimization and Control · Mathematics 2018-03-30 Nicolas Loizou , Peter Richtárik

1. Complex systems of moving and interacting objects are ubiquitous in the natural and social sciences. Predicting their behavior often requires models that mimic these systems with sufficient accuracy, while accounting for their inherent…

Quantitative Methods · Quantitative Biology 2014-12-02 Jonathan R. Potts , Marie Auger-Méthé , Karl Mokross , Mark A. Lewis

We study the learning ability of linear recurrent neural networks with Gradient Descent. We prove the first theoretical guarantee on linear RNNs to learn any stable linear dynamic system using any a large type of loss functions. For an…

Machine Learning · Computer Science 2023-10-24 Lifu Wang , Tianyu Wang , Shengwei Yi , Bo Shen , Bo Hu , Xing Cao

A restricted Boltzmann machine (RBM) is a generative neural-network model with many novel applications such as collaborative filtering and acoustic modeling. An RBM lacks the capacity to retain memory, making it inappropriate for dynamic…

Machine Learning · Statistics 2018-05-01 Jefferson Hernandez , Andres G. Abad

Deep neural networks have dramatically achieved great success on a variety of challenging tasks. However, most successful DNNs have an extremely complex structure, leading to extensive research on model compression.As a significant area of…

Machine Learning · Computer Science 2020-04-13 Haipeng Jia , Xueshuang Xiang , Da Fan , Meiyu Huang , Changhao Sun , Yang He

We prove that stochastic gradient descent efficiently converges to the global optimizer of the maximum likelihood objective of an unknown linear time-invariant dynamical system from a sequence of noisy observations generated by the system.…

Machine Learning · Computer Science 2019-02-12 Moritz Hardt , Tengyu Ma , Benjamin Recht

This article provides an original understanding of the behavior of a class of graph-oriented semi-supervised learning algorithms in the limit of large and numerous data. It is demonstrated that the intuition at the root of these methods…

Machine Learning · Computer Science 2017-11-10 Xiaoyi Mai , Romain Couillet

The training of modern machine learning models often consists in solving high-dimensional non-convex optimisation problems that are subject to large-scale data. In this context, momentum-based stochastic optimisation algorithms have become…

Optimization and Control · Mathematics 2024-11-06 Kexin Jin , Jonas Latz , Chenguang Liu , Alessandro Scagliotti

Bayesian neural networks and deep ensembles represent two modern paradigms of uncertainty quantification in deep learning. Yet these approaches struggle to scale mainly due to memory inefficiency issues, since they require parameter storage…

Machine Learning · Statistics 2021-11-24 Hippolyt Ritter , Martin Kukla , Cheng Zhang , Yingzhen Li