English
Related papers

Related papers: How Controlling the Variance can Improve Training …

200 papers

In this work, we study scaling limits of shallow Bayesian neural networks (BNNs) via their connection to Gaussian processes (GPs), with an emphasis on statistical modeling, identifiability, and scalable inference. We first establish a…

Machine Learning · Statistics 2026-02-27 Gracielle Antunes de Araújo , Flávio B. Gonçalves

In this work, we investigate the use of sparsity-inducing regularizers during training of Convolution Neural Networks (CNNs). These regularizers encourage that fewer connections in the convolution and fully connected layers take non-zero…

Computer Vision and Pattern Recognition · Computer Science 2014-12-04 Maxwell D. Collins , Pushmeet Kohli

Graph Convolutional Networks (GCNs) are extensively utilized for deep learning on graphs. The large data sizes of graphs and their vertex features make scalable training algorithms and distributed memory systems necessary. Since the…

Machine Learning · Computer Science 2022-12-14 Gunduz Vehbi Demirci , Aparajita Haldar , Hakan Ferhatosmanoglu

Parallel training of neural networks at scale is challenging due to significant overheads arising from communication. Recently, deep learning researchers have developed a variety of pruning algorithms that are capable of pruning (i.e.…

Machine Learning · Computer Science 2023-05-16 Siddharth Singh , Abhinav Bhatele

Understanding when neural networks can be learned efficiently is a fundamental question in learning theory. Existing hardness results suggest that assumptions on both the input distribution and the network's weights are necessary for…

Machine Learning · Computer Science 2023-10-05 Amit Daniely , Nathan Srebro , Gal Vardi

We focus on a specific class of shallow neural networks with a single hidden layer, namely those with $L_2$-normalised data and either a sigmoid-shaped Gaussian error function ("erf") activation or a Gaussian Error Linear Unit (GELU)…

Machine Learning · Computer Science 2022-10-21 Felix Biggs , Benjamin Guedj

We study the problem of training deep neural networks with Rectified Linear Unit (ReLU) activation function using gradient descent and stochastic gradient descent. In particular, we study the binary classification problem and show that for…

Machine Learning · Computer Science 2018-12-31 Difan Zou , Yuan Cao , Dongruo Zhou , Quanquan Gu

Sparse training has emerged as a promising method for resource-efficient deep neural networks (DNNs) in real-world applications. However, the reliability of sparse models remains a crucial concern, particularly in detecting unknown…

Machine Learning · Computer Science 2024-04-01 Bowen Lei , Dongkuan Xu , Ruqi Zhang , Bani Mallick

We propose an efficient optimization algorithm for selecting a subset of training data to induce sparsity for Gaussian process regression. The algorithm estimates an inducing set and the hyperparameters using a single objective, either the…

Machine Learning · Computer Science 2013-11-12 Yanshuai Cao , Marcus A. Brubaker , David J. Fleet , Aaron Hertzmann

There is a growing literature on the study of large-width properties of deep Gaussian neural networks (NNs), i.e. deep NNs with Gaussian-distributed parameters or weights, and Gaussian stochastic processes. Motivated by some empirical and…

Machine Learning · Computer Science 2023-04-11 Alberto Bordino , Stefano Favaro , Sandra Fortini

We perform an empirical study of the behaviour of deep networks when fully linearizing some of its feature channels through a sparsity prior on the overall number of nonlinear units in the network. In experiments on image classification and…

Machine Learning · Computer Science 2023-06-02 Christian H. X. Ali Mehmeti-Göpel , Jan Disselhoff

We systematically analyze optimization dynamics in deep neural networks (DNNs) trained with stochastic gradient descent (SGD) and study the effect of learning rate $\eta$, depth $d$, and width $w$ of the neural network. By analyzing the…

Machine Learning · Computer Science 2023-10-25 Dayal Singh Kalra , Maissam Barkeshli

In this note we present a generative model of natural images consisting of a deep hierarchy of layers of latent random variables, each of which follows a new type of distribution that we call rectified Gaussian. These rectified Gaussian…

Machine Learning · Statistics 2016-03-01 Tim Salimans

Deep neural networks are strongly over-parameterized, often containing far more weights than required for their task. Although such redundancy can aid optimization, it leads to inefficient deployment and high computational cost, motivating…

Disordered Systems and Neural Networks · Physics 2026-02-18 Diego Pesce , Yang-Hui He , Guido Caldarelli

Deep Gaussian Processes (DGP) are hierarchical generalizations of Gaussian Processes (GP) that have proven to work effectively on a multiple supervised regression tasks. They combine the well calibrated uncertainty estimates of GPs with the…

Machine Learning · Statistics 2018-01-10 Marton Havasi , José Miguel Hernández-Lobato , Juan José Murillo-Fuentes

Factorized layers--operations parameterized by products of two or more matrices--occur in a variety of deep learning contexts, including compressed model training, certain types of knowledge distillation, and multi-head self-attention…

Machine Learning · Statistics 2022-10-07 Mikhail Khodak , Neil Tenenholtz , Lester Mackey , Nicolò Fusi

We study the behavior of untrained neural networks whose weights and biases are randomly distributed using mean field theory. We show the existence of depth scales that naturally limit the maximum depth of signal propagation through these…

Machine Learning · Statistics 2017-04-06 Samuel S. Schoenholz , Justin Gilmer , Surya Ganguli , Jascha Sohl-Dickstein

A longstanding goal in deep learning research has been to precisely characterize training and generalization. However, the often complex loss landscapes of neural networks have made a theory of learning dynamics elusive. In this work, we…

We study in this paper how to initialize the parameters of multinomial logistic regression (a fully connected layer followed with softmax and cross entropy loss), which is widely used in deep neural network (DNN) models for classification…

Computer Vision and Pattern Recognition · Computer Science 2018-09-18 Bowen Cheng , Rong Xiao , Yandong Guo , Yuxiao Hu , Jianfeng Wang , Lei Zhang

Machine/deep-learning (ML/DL) based techniques are emerging as a driving force behind many cutting-edge technologies, achieving high accuracy on computer vision workloads such as image classification and object detection. However, training…

‹ Prev 1 3 4 5 6 7 10 Next ›