English
Related papers

Related papers: Decoupled Weight Decay for Any $p$ Norm

200 papers

Network (or graph) sparsification compresses a graph by removing inessential edges. By reducing the data volume, it accelerates or even facilitates many downstream analyses. Still, the accuracy of many sparsification methods, with…

Social and Information Networks · Computer Science 2023-09-28 Zhen Su , Jürgen Kurths , Henning Meyerhenke

While there are many studies on weight regularization, the study on structure regularization is rare. Many existing systems on structured prediction focus on increasing the level of structural dependencies within the model. However, this…

Machine Learning · Computer Science 2015-02-02 Xu Sun

Overfitting is one of the most common problems when training deep neural networks on comparatively small datasets. Here, we demonstrate that neural network activation sparsity is a reliable indicator for overfitting which we utilize to…

Machine Learning · Computer Science 2020-02-24 Karim Huesmann , Soeren Klemm , Lars Linsen , Benjamin Risse

We investigate the generalization and optimization properties of shallow neural-network classifiers trained by gradient descent in the interpolating regime. Specifically, in a realizable scenario where model weights can achieve arbitrarily…

Machine Learning · Statistics 2023-03-29 Hossein Taheri , Christos Thrampoulidis

Deep neural networks (DNNs) have become increasingly important due to their excellent empirical performance on a wide range of problems. However, regularization is generally achieved by indirect means, largely due to the complex set of…

Machine Learning · Computer Science 2018-07-02 Amal Rannen Triki , Maxim Berman , Matthew B. Blaschko

In seeking for sparse and efficient neural network models, many previous works investigated on enforcing L1 or L0 regularizers to encourage weight sparsity during training. The L0 regularizer measures the parameter sparsity directly and is…

Machine Learning · Computer Science 2020-01-22 Huanrui Yang , Wei Wen , Hai Li

The large capacity of neural networks enables them to learn complex functions. To avoid overfitting, networks however require a lot of training data that can be expensive and time-consuming to collect. A common practical approach to…

Machine Learning · Computer Science 2020-03-10 Majed El Helou , Frederike Dümbgen , Sabine Süsstrunk

Sparse neural networks are important for achieving better generalization and enhancing computation efficiency. This paper proposes a novel learning approach to obtain sparse fully connected layers in neural networks (NNs) automatically. We…

Machine Learning · Computer Science 2021-04-28 Mengqiao Han , Xiabi Liu , Zhaoyang Hai , Zhengwen Li

Deep reinforcement learning(DRL) has shown significant promise in a wide range of applications including computer games and robotics. Yet, training DRL policies consume extraordinary computing resources resulting in dense policies which are…

Machine Learning · Computer Science 2024-03-12 Vikram Goddla

The sparse linear reconstruction problem is a core problem in signal processing which aims to recover sparse solutions to linear systems. The original problem regularized by the total number of nonzero components (also known as $L_0$…

Optimization and Control · Mathematics 2025-11-19 Yuyuan Ouyang , Kyle Yates

In this paper, we propose embedding sparsity into the structure of deep neural networks, where model parameters can be exactly zero during training with the stochastic gradient descent. Thus, it can learn the sparsified structure and the…

Machine Learning · Computer Science 2020-06-25 Yongjin Lee

We present a method for supervised learning of sparsity-promoting regularizers for denoising signals and images. Sparsity-promoting regularization is a key ingredient in solving modern signal reconstruction problems; however, the operators…

Machine Learning · Computer Science 2023-09-07 Avrajit Ghosh , Michael T. McCann , Madeline Mitchell , Saiprasad Ravishankar

Sparsity is one of the key concepts that allows the recovery of signals that are subsampled at a rate significantly lower than required by the Nyquist-Shannon sampling theorem. Our proposed framework uses arbitrary multiscale transforms,…

Optimization and Control · Mathematics 2017-05-31 Jackie Ma , Maximilian März

Regularization is typically understood as improving generalization by altering the landscape of local extrema to which the model eventually converges. Deep neural networks (DNNs), however, challenge this view: We show that removing…

Machine Learning · Computer Science 2019-06-03 Aditya Golatkar , Alessandro Achille , Stefano Soatto

Deep neural networks are typically trained by optimizing a loss function with an SGD variant, in conjunction with a decaying learning rate, until convergence. We show that simple averaging of multiple points along the trajectory of SGD,…

Machine Learning · Computer Science 2019-02-26 Pavel Izmailov , Dmitrii Podoprikhin , Timur Garipov , Dmitry Vetrov , Andrew Gordon Wilson

A low precision deep neural network training technique for producing sparse, ternary neural networks is presented. The technique incorporates hard- ware implementation costs during training to achieve significant model compression for…

Computer Vision and Pattern Recognition · Computer Science 2017-10-11 Julian Faraone , Nicholas Fraser , Giulio Gambardella , Michaela Blott , Philip H. W. Leong

We provide a new efficient version of the backpropagation algorithm, specialized to the case where the weights of the neural network being trained are sparse. Our algorithm is general, as it applies to arbitrary (unstructured) sparsity and…

Machine Learning · Computer Science 2023-02-10 Mahdi Nikdan , Tommaso Pegolotti , Eugenia Iofinova , Eldar Kurtic , Dan Alistarh

Finding neural network weights that generalize well from small datasets is difficult. A promising approach is to learn a weight initialization such that a small number of weight changes results in low generalization error. We show that this…

Weight decay is a broadly used technique for training state-of-the-art deep networks from image classification to large language models. Despite its widespread usage and being extensively studied in the classical literature, its role…

Machine Learning · Computer Science 2024-11-06 Francesco D'Angelo , Maksym Andriushchenko , Aditya Varre , Nicolas Flammarion

Recent works have shown that on sufficiently over-parametrized neural nets, gradient descent with relatively large initialization optimizes a prediction function in the RKHS of the Neural Tangent Kernel (NTK). This analysis leads to global…

Machine Learning · Statistics 2020-04-28 Colin Wei , Jason D. Lee , Qiang Liu , Tengyu Ma
‹ Prev 1 4 5 6 7 8 10 Next ›