English
Related papers

Related papers: Optimization Theory for ReLU Neural Networks Train…

200 papers

In a neural network with ReLU activations, the number of piecewise linear regions in the output can grow exponentially with depth. However, this is highly unlikely to happen when the initial parameters are sampled randomly, which therefore…

Machine Learning · Computer Science 2025-10-17 Max Milkert , David Hyde , Forrest Laine

Deep neural networks (DNNs), particularly those using Rectified Linear Unit (ReLU) activation functions, have achieved remarkable success across diverse machine learning tasks, including image recognition, audio processing, and language…

Machine Learning · Computer Science 2026-03-26 Emi Zeger , Mert Pilanci

Recent results suggest that reinitializing a subset of the parameters of a neural network during training can improve generalization, particularly for small training sets. We study the impact of different reinitialization methods in several…

Machine Learning · Computer Science 2021-09-02 Ibrahim Alabdulmohsin , Hartmut Maennel , Daniel Keysers

A key component of most neural network architectures is the use of normalization layers, such as Batch Normalization. Despite its common use and large utility in optimizing deep architectures, it has been challenging both to generically…

Machine Learning · Computer Science 2020-02-17 Cecilia Summers , Michael J. Dinneen

Understanding the fundamental principles behind the success of deep neural networks is one of the most important open questions in the current literature. To this end, we study the training problem of deep neural networks and introduce an…

Machine Learning · Computer Science 2023-09-27 Tolga Ergen , Mert Pilanci

The lack of mathematical tractability of Deep Neural Networks (DNNs) has hindered progress towards having a unified convergence analysis of training algorithms, in the general setting. We propose a unified optimization framework for…

Machine Learning · Computer Science 2018-05-24 Hadi Ghauch , Hossein Shokri-Ghadikolaei , Carlo Fischione , Mikael Skoglund

An old idea in optimization theory says that since the gradient is a dual vector it may not be subtracted from the weights without first being mapped to the primal space where the weights reside. We take this idea seriously in this paper…

Machine Learning · Computer Science 2024-12-09 Jeremy Bernstein , Laker Newhouse

While deep learning has outperformed other methods for various tasks, theoretical frameworks that explain its reason have not been fully established. To address this issue, we investigate the excess risk of two-layer ReLU neural networks in…

Machine Learning · Statistics 2022-06-07 Shunta Akiyama , Taiji Suzuki

Understanding implicit bias of gradient descent for generalization capability of ReLU networks has been an important research topic in machine learning research. Unfortunately, even for a single ReLU neuron trained with the square loss, it…

Machine Learning · Computer Science 2022-06-14 Sangmin Lee , Byeongsu Sim , Jong Chul Ye

Unraveling the reasons behind the remarkable success and exceptional generalization capabilities of deep neural networks presents a formidable challenge. Recent insights from random matrix theory, specifically those concerning the spectral…

Machine Learning · Statistics 2023-04-10 Xuanzhe Xiao , Zeng Li , Chuanlong Xie , Fengwei Zhou

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

We introduce a general theoretical framework, designed for the study of gradient optimisation of deep neural networks, that encompasses ubiquitous architecture choices including batch normalisation, weight normalisation and skip…

Machine Learning · Computer Science 2023-12-05 Lachlan Ewen MacDonald , Jack Valmadre , Hemanth Saratchandran , Simon Lucey

We design a ReLU-based multilayer neural network by mapping the feature vectors to a higher dimensional space in every layer. We design the weight matrices in every layer to ensure a reduction of the training cost as the number of layers…

Machine Learning · Computer Science 2020-10-28 Alireza M. Javid , Arun Venkitaraman , Mikael Skoglund , Saikat Chatterjee

Batch-normalization (BN) layers are thought to be an integrally important layer type in today's state-of-the-art deep convolutional neural networks for computer vision tasks such as classification and detection. However, BN layers introduce…

Machine Learning · Computer Science 2019-07-23 Mark D. McDonnell , Hesham Mostafa , Runchun Wang , Andre van Schaik

Large neural networks have proved remarkably effective in modern deep learning practice, even in the overparametrized regime where the number of active parameters is large relative to the sample size. This contradicts the classical…

Machine Learning · Computer Science 2023-08-01 Huiyuan Wang , Wei Lin

Recent works have highlighted scale invariance or symmetry present in the weight space of a typical deep network and the adverse effect it has on the Euclidean gradient based stochastic gradient descent optimization. In this work, we show…

Machine Learning · Computer Science 2015-11-04 Vijay Badrinarayanan , Bamdev Mishra , Roberto Cipolla

Deep Neural Networks have achieved remarkable success relying on the developing high computation capability of GPUs and large-scale datasets with increasing network depth and width in image recognition, object detection and many other…

Machine Learning · Computer Science 2020-01-08 E Zhenqian , Gao Weiguo

We give a simple proof for the global convergence of gradient descent in training deep ReLU networks with the standard square loss, and show some of its improvements over the state-of-the-art. In particular, while prior works require all…

Machine Learning · Computer Science 2021-06-14 Quynh Nguyen

A common method in training neural networks is to initialize all the weights to be independent Gaussian vectors. We observe that by instead initializing the weights into independent pairs, where each pair consists of two identical Gaussian…

Machine Learning · Computer Science 2022-06-28 Alexander Munteanu , Simon Omlor , Zhao Song , David P. Woodruff

Batch normalization is widely used in deep learning to normalize intermediate activations. Deep networks suffer from notoriously increased training complexity, mandating careful initialization of weights, requiring lower learning rates,…

Machine Learning · Statistics 2022-10-19 Lakshmi Annamalai , Chetan Singh Thakur