English
Related papers

Related papers: Optimized Weight Initialization on the Stiefel Man…

200 papers

It is notoriously difficult to train Transformers on small datasets; typically, large pre-trained models are instead used as the starting point. We explore the weights of such pre-trained Transformers (particularly for vision) to attempt to…

Computer Vision and Pattern Recognition · Computer Science 2023-05-18 Asher Trockman , J. Zico Kolter

The success of deep neural networks is in part due to the use of normalization layers. Normalization layers like Batch Normalization, Layer Normalization and Weight Normalization are ubiquitous in practice, as they improve generalization…

Machine Learning · Computer Science 2020-06-15 Yonatan Dukler , Quanquan Gu , Guido Montúfar

It is well known that the initialization of weights in deep neural networks can have a dramatic impact on learning speed. For example, ensuring the mean squared singular value of a network's input-output Jacobian is $O(1)$ is essential for…

Machine Learning · Computer Science 2017-11-15 Jeffrey Pennington , Samuel S. Schoenholz , Surya Ganguli

Activation functions influence behavior and performance of DNNs. Nonlinear activation functions, like Rectified Linear Units (ReLU), Exponential Linear Units (ELU) and Scaled Exponential Linear Units (SELU), outperform the linear…

Neural and Evolutionary Computing · Computer Science 2019-02-05 Alberto Marchisio , Muhammad Abdullah Hanif , Semeen Rehman , Maurizio Martina , Muhammad Shafique

In artificial neural network, the activation function and the weight initialization method play important roles in training and performance of a neural network. The question arises is what properties of a function are important/necessary…

Neural and Evolutionary Computing · Computer Science 2020-04-15 Leonid Datta

Activation functions critically influence trainability and expressivity, and recent work has therefore explored a broad range of nonlinearities. However, widely used Gaussian i.i.d. initializations are designed to preserve activation…

Machine Learning · Computer Science 2025-12-17 Hyunwoo Lee , Hayoung Choi , Hyunju Kim

Weight decay is one of the most widely used forms of regularization in deep learning, and has been shown to improve generalization and robustness. The optimization objective driving weight decay is a sum of losses plus a term proportional…

Machine Learning · Computer Science 2023-07-07 Liu Yang , Jifan Zhang , Joseph Shenouda , Dimitris Papailiopoulos , Kangwook Lee , Robert D. Nowak

The successful training of neural networks hinges on the use of first order optimization methods, yet the theoretical characterization of these methods remains incomplete. This is especially true in settings with mild overparameterization.…

Machine Learning · Computer Science 2026-05-27 James Town , Etienne Boursier , Ben Lewis , Matthias Englert , Ranko Lazic

Proper initialisation strategy is of primary importance to mitigate gradient explosion or vanishing when training neural networks. Yet, the impact of initialisation parameters still lacks a precise theoretical understanding for several…

Machine Learning · Computer Science 2026-05-12 Andrea Combette , Antoine Venaille , Nelly Pustelnik

Binary neural networks improve computationally efficiency of deep models with a large margin. However, there is still a performance gap between a successful full-precision training and binary training. We bring some insights about why this…

Machine Learning · Computer Science 2020-04-22 Xinlin Li , Vahid Partovi Nia

This paper introduces an extension of the backpropagation algorithm that enables us to have layers with constrained weights in a deep network. In particular, we make use of the Riemannian geometry and optimization techniques on matrix…

Computer Vision and Pattern Recognition · Computer Science 2016-11-21 Mehrtash Harandi , Basura Fernando

Optimal parameter initialization remains a crucial problem for neural network training. A poor weight initialization may take longer to train and/or converge to sub-optimal solutions. Here, we propose a method of weight re-initialization by…

Machine Learning · Computer Science 2021-04-21 Norman Mu , Zhewei Yao , Amir Gholami , Kurt Keutzer , Michael Mahoney

Deep networks are gradually penetrating almost every domain in our lives due to their amazing success. However, with substantive performance accuracy improvements comes the price of \emph{irreproducibility}. Two identical models, trained on…

Machine Learning · Computer Science 2020-12-02 Gil I. Shamir , Dong Lin , Lorenzo Coviello

We propose ReDense as a simple and low complexity way to improve the performance of trained neural networks. We use a combination of random weights and rectified linear unit (ReLU) activation function to add a ReLU dense (ReDense) layer to…

Machine Learning · Computer Science 2020-10-27 Alireza M. Javid , Sandipan Das , Mikael Skoglund , Saikat Chatterjee

The performance of gradient-based optimization strategies depends heavily on the initial weights of the parametric model. Recent works show that there exist weight initializations from which optimization procedures can find the…

Machine Learning · Computer Science 2020-01-23 Rafael Rego Drumond , Lukas Brinkmeyer , Josif Grabocka , Lars Schmidt-Thieme

The weight initialization and the activation function of deep neural networks have a crucial impact on the performance of the training procedure. An inappropriate selection can lead to the loss of information of the input during forward…

Machine Learning · Statistics 2019-05-28 Soufiane Hayou , Arnaud Doucet , Judith Rousseau

We propose and analyze a new family of algorithms for training neural networks with ReLU activations. Our algorithms are based on the technique of alternating minimization: estimating the activation patterns of each ReLU for all given…

Machine Learning · Computer Science 2018-10-12 Gauri Jagatap , Chinmay Hegde

Deep neural networks have achieved remarkable accomplishments in practice. The success of these networks hinges on effective initialization methods, which are vital for ensuring stable and rapid convergence during training. Recently,…

Machine Learning · Computer Science 2025-03-11 Yu Pan , Chaozheng Wang , Zekai Wu , Qifan Wang , Min Zhang , Zenglin Xu

Many modern neural network architectures are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Sufficiently overparameterized neural network architectures in principle have the…

Machine Learning · Computer Science 2019-02-14 Samet Oymak , Mahdi Soltanolkotabi

The growing interest in satellite imagery has triggered the need for efficient mechanisms to extract valuable information from these vast data sources, providing deeper insights. Even though deep learning has shown significant progress in…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Wadii Boulila , Eman Alshanqiti , Ayyub Alzahem , Anis Koubaa , Nabil Mlaiki