English
Related papers

Related papers: Weight-Sharing Regularization

200 papers

We introduce a novel stochastic regularization technique for deep neural networks, which decomposes a layer into multiple branches with different parameters and merges stochastically sampled combinations of the outputs from the branches…

Machine Learning · Computer Science 2019-10-04 Wonpyo Park , Paul Hongsuck Seo , Bohyung Han , Minsu Cho

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

Modern optimizers such as AdamW, equipped with momentum and adaptive learning rate, are designed to escape local minima and explore the vast parameter space. This exploration is beneficial for finding good loss basins when training from…

Machine Learning · Computer Science 2024-11-05 Junjiao Tian , Chengyue Huang , Zsolt Kira

With the success of deep neural networks, Neural Architecture Search (NAS) as a way of automatic model design has attracted wide attention. As training every child model from scratch is very time-consuming, recent works leverage…

Machine Learning · Computer Science 2020-01-07 Yuge Zhang , Zejun Lin , Junyang Jiang , Quanlu Zhang , Yujing Wang , Hui Xue , Chen Zhang , Yaming Yang

Regularization techniques such as $\mathcal{L}_1$ and $\mathcal{L}_2$ regularizers are effective in sparsifying neural networks (NNs). However, to remove a certain neuron or channel in NNs, all weight elements related to that neuron or…

Machine Learning · Computer Science 2023-05-31 Ali Haisam Muhammad Rafid , Adrian Sandu

Many different deep networks have been used to approximate, accelerate or improve traditional image operators. Among these traditional operators, many contain parameters which need to be tweaked to obtain the satisfactory results, which we…

Computer Vision and Pattern Recognition · Computer Science 2019-07-15 Qingnan Fan , Dongdong Chen , Lu Yuan , Gang Hua , Nenghai Yu , Baoquan Chen

Transfer learning have been frequently used to improve deep neural network training through incorporating weights of pre-trained networks as the starting-point of optimization for regularization. While deep transfer learning can usually…

Machine Learning · Computer Science 2019-11-19 Ruosi Wan , Haoyi Xiong , Xingjian Li , Zhanxing Zhu , Jun Huan

Given a length $n$ sample from $\mathbb{R}^d$ and a neural network with a fixed architecture with $W$ weights, $k$ neurons, linear threshold activation functions, and binary outputs on each neuron, we study the problem of uniformly sampling…

Machine Learning · Computer Science 2019-12-12 Changlong Wu , Narayana Prasad Santhanam

Deep neural networks (DNNs) are quantized for efficient inference on resource-constrained platforms. However, training deep learning models with low-precision weights and activations involves a demanding optimization task, which calls for…

Machine Learning · Computer Science 2021-05-25 Ziang Long , Penghang Yin , Jack Xin

Very large-scale Deep Neural Networks (DNNs) have achieved remarkable successes in a large variety of computer vision tasks. However, the high computation intensity of DNNs makes it challenging to deploy these models on resource-limited…

Computer Vision and Pattern Recognition · Computer Science 2017-07-26 Wei Wen , Cong Xu , Chunpeng Wu , Yandan Wang , Yiran Chen , Hai Li

Continuous-depth neural networks can be viewed as deep limits of discrete neural networks whose dynamics resemble a discretization of an ordinary differential equation (ODE). Although important steps have been taken to realize the…

Neural and Evolutionary Computing · Computer Science 2020-12-09 François-Xavier Vialard , Roland Kwitt , Susan Wei , Marc Niethammer

Training a neural network using backpropagation algorithm requires passing error gradients sequentially through the network. The backward locking prevents us from updating network layers in parallel and fully leveraging the computing…

Machine Learning · Computer Science 2019-05-30 Zhouyuan Huo , Bin Gu , Heng Huang

The ever-increasing number of parameters in deep neural networks poses challenges for memory-limited applications. Regularize-and-prune methods aim at meeting these challenges by sparsifying the network weights. In this context we quantify…

Machine Learning · Computer Science 2018-10-30 Enzo Tartaglione , Skjalg Lepsøy , Attilio Fiandrotti , Gianluca Francini

Deep learning uses neural networks which are parameterised by their weights. The neural networks are usually trained by tuning the weights to directly minimise a given loss function. In this paper we propose to re-parameterise the weights…

Neural and Evolutionary Computing · Computer Science 2022-03-14 Michael Fairbank , Spyridon Samothrakis , Luca Citi

Improving the generalization ability of modern deep neural networks (DNNs) is a fundamental challenge in machine learning. Two branches of methods have been proposed to seek flat minima and improve generalization: one led by sharpness-aware…

Machine Learning · Computer Science 2024-04-02 Tao Li , Qinghua Tao , Weihao Yan , Zehao Lei , Yingwen Wu , Kun Fang , Mingzhen He , Xiaolin Huang

Deep learning models have been successfully used in computer vision and many other fields. We propose an unorthodox algorithm for performing quantization of the model parameters. In contrast with popular quantization schemes based on…

Machine Learning · Computer Science 2018-11-27 Maxim Naumov , Utku Diril , Jongsoo Park , Benjamin Ray , Jedrzej Jablonski , Andrew Tulloch

Weight sharing, equivariance, and local filters, as in convolutional neural networks, are believed to contribute to the sample efficiency of neural networks. However, it is not clear how each one of these design choices contributes to the…

Machine Learning · Computer Science 2025-01-27 Arash Behboodi , Gabriele Cesa

Recent results show that deep neural networks achieve excellent performance even when, during training, weights are quantized and projected to a binary representation. Here, we show that this is just the tip of the iceberg: these same…

Neural and Evolutionary Computing · Computer Science 2016-06-08 Paul Merolla , Rathinakumar Appuswamy , John Arthur , Steve K. Esser , Dharmendra Modha

Cross-view geo-localization aims to spot images of the same location shot from two platforms, e.g., the drone platform and the satellite platform. Existing methods usually focus on optimizing the distance between one embedding with others…

Computer Vision and Pattern Recognition · Computer Science 2022-11-11 Tingyu Wang , Zhedong Zheng , Zunjie Zhu , Yuhan Gao , Yi Yang , Chenggang Yan

The optimisation of neural networks can be sped up by orthogonalising the gradients before the optimisation step, ensuring the diversification of the learned representations. We orthogonalise the gradients of the layer's components/filters…

Machine Learning · Computer Science 2022-02-16 Mark Tuddenham , Adam Prügel-Bennett , Jonathan Hare