English
Related papers

Related papers: Randomly Initialized One-Layer Neural Networks Mak…

200 papers

Linear networks provide valuable insights into the workings of neural networks in general. This paper identifies conditions under which the gradient flow provably trains a linear network, in spite of the non-strict saddle points present in…

Optimization and Control · Mathematics 2020-06-30 Armin Eftekhari

We present a global algorithm for training multilayer neural networks in this Letter. The algorithm is focused on controlling the local fields of neurons induced by the input of samples by random adaptations of the synaptic weights. Unlike…

Biological Physics · Physics 2007-05-23 Hong Zhao , Tao Jin

Successfully training deep neural networks often requires either batch normalization, appropriate weight initialization, both of which come with their own challenges. We propose an alternative, geometrically motivated method for training.…

Machine Learning · Computer Science 2019-10-08 Aram-Alexandre Pooladian , Chris Finlay , Adam M Oberman

State-of-the-art, high capacity deep neural networks not only require large amounts of labelled training data, they are also highly susceptible to label errors in this data, typically resulting in large efforts and costs and therefore…

Machine Learning · Computer Science 2020-07-20 Christian Haase-Schütz , Rainer Stal , Heinz Hertlein , Bernhard Sick

When optimizing over-parameterized models, such as deep neural networks, a large set of parameters can achieve zero training error. In such cases, the choice of the optimization algorithm and its respective hyper-parameters introduces…

Machine Learning · Computer Science 2019-12-06 Gauthier Gidel , Francis Bach , Simon Lacoste-Julien

The identification of a linear system model from data has wide applications in control theory. The existing work that provides finite sample guarantees for linear system identification typically uses data from a single long system…

Machine Learning · Statistics 2025-05-09 Lei Xin , Baike She , Qi Dou , George Chiu , Shreyas Sundaram

Overparameterization refers to the important phenomenon where the width of a neural network is chosen such that learning algorithms can provably attain zero loss in nonconvex training. The existing theory establishes such global convergence…

Machine Learning · Computer Science 2021-11-04 Chaehwan Song , Ali Ramezani-Kebrya , Thomas Pethick , Armin Eftekhari , Volkan Cevher

Deep neural networks are powerful tools to model observations over time with non-linear patterns. Despite the widespread use of neural networks in such settings, most theoretical developments of deep neural networks are under the assumption…

Machine Learning · Statistics 2022-10-24 Mingliang Ma , Abolfazl Safikhani

Designing models that are both expressive and preserve known invariances of tasks is an increasingly hard problem. Existing solutions tradeoff invariance for computational or memory resources. In this work, we show how to leverage…

Machine Learning · Computer Science 2023-09-29 Leonardo Cotta , Gal Yehuda , Assaf Schuster , Chris J. Maddison

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

This work studies approximation based on single-hidden-layer feedforward and recurrent neural networks with randomly generated internal weights. These methods, in which only the last layer of weights and a few hyperparameters are optimized,…

Probability · Mathematics 2021-02-17 Lukas Gonon , Lyudmila Grigoryeva , Juan-Pablo Ortega

For the efficient execution of deep convolutional neural networks (CNN) on edge devices, various approaches have been presented which reduce the bit width of the network parameters down to 1 bit. Binarization of the first layer was always…

Machine Learning · Computer Science 2018-12-11 Robert Dürichen , Thomas Rocznik , Oliver Renz , Christian Peters

Most deep neural networks are trained under fixed network architectures and require retraining when the architecture changes. If expanding the network's size is needed, it is necessary to retrain from scratch, which is expensive. To avoid…

Machine Learning · Computer Science 2023-11-09 Chau Pham , Piotr Teterwak , Soren Nelson , Bryan A. Plummer

We study nonlinear regression of real valued data in an individual sequence manner, where we provide results that are guaranteed to hold without any statistical assumptions. We address the convergence and undertraining issues of…

Machine Learning · Computer Science 2014-10-08 N. Denizcan Vanli , Muhammed O. Sayin , Suleyman S. Kozat

The Multi-Prize Lottery Ticket Hypothesis posits that randomly initialized neural networks contain several subnetworks that achieve comparable accuracy to fully trained models of the same architecture. However, current methods require that…

Machine Learning · Computer Science 2023-03-29 Matt Gorbett , Darrell Whitley

This work develops the global equations of neural networks through stacked piecewise manifolds, fixed-point theory, and boundary-conditioned iteration. Once fixed coordinates and operators are removed, a neural network appears as a…

Machine Learning · Computer Science 2025-12-09 Max Y. Ma , Gen-Hua Shi

In this paper, we present a novel approach to perform deep neural networks layer-wise weight initialization using Linear Discriminant Analysis (LDA). Typically, the weights of a deep neural network are initialized with: random values,…

Computer Vision and Pattern Recognition · Computer Science 2017-11-27 Michele Alberti , Mathias Seuret , Vinaychandran Pondenkandath , Rolf Ingold , Marcus Liwicki

Accurate modeling of complex physical problems, such as fluid-structure interaction, requires multiphysics coupling across the interface, which often has intricate geometry and dynamic boundaries. Conventional numerical methods face…

Numerical Analysis · Mathematics 2023-08-08 Yunlong Li , Fei Wang

Many real world vision tasks, such as reflection removal from a transparent surface and intrinsic image decomposition, can be modeled as single image layer separation. However, this problem is highly ill-posed, requiring accurately aligned…

Computer Vision and Pattern Recognition · Computer Science 2019-09-10 Yunfei Liu , Feng Lu

Artificial neural networks are functions depending on a finite number of parameters typically encoded as weights and biases. The identification of the parameters of the network from finite samples of input-output pairs is often referred to…

Machine Learning · Computer Science 2022-11-10 Massimo Fornasier , Timo Klock , Marco Mondelli , Michael Rauchensteiner