English
Related papers

Related papers: Differentiable Sparsity via $D$-Gating: Simple and…

200 papers

We study the implicit regularization of gradient descent towards structured sparsity via a novel neural reparameterization, which we call a diagonally grouped linear neural network. We show the following intriguing property of our…

Machine Learning · Statistics 2023-01-31 Jiangyuan Li , Thanh V. Nguyen , Chinmay Hegde , Raymond K. W. Wong

The parameters of a neural network are naturally organized in groups, some of which might not contribute to its overall performance. To prune out unimportant groups of parameters, we can include some non-differentiable penalty to the…

Machine Learning · Computer Science 2023-01-06 Tristan Deleu , Yoshua Bengio

Deep neural networks have significantly alleviated the burden of feature engineering, but comparable efforts are now required to determine effective architectures for these networks. Furthermore, as network sizes have become excessively…

Machine Learning · Computer Science 2023-10-25 Yognjin Lee

In this paper, we consider the joint task of simultaneously optimizing (i) the weights of a deep neural network, (ii) the number of neurons for each hidden layer, and (iii) the subset of active input features (i.e., feature selection).…

Machine Learning · Statistics 2017-02-14 Simone Scardapane , Danilo Comminiello , Amir Hussain , Aurelio Uncini

In the light of the fact that the stochastic gradient descent (SGD) often finds a flat minimum valley in the training loss, we propose a novel directional pruning method which searches for a sparse minimizer in or close to that flat region.…

Machine Learning · Computer Science 2020-10-15 Shih-Kang Chao , Zhanyu Wang , Yue Xing , Guang Cheng

Differentially private stochastic gradient descent (DP-SGD) is broadly considered to be the gold standard for training and fine-tuning neural networks under differential privacy (DP). With the increasing availability of high-quality…

The performance of trained neural networks is robust to harsh levels of pruning. Coupled with the ever-growing size of deep learning models, this observation has motivated extensive research on learning sparse models. In this work, we focus…

Machine Learning · Computer Science 2022-11-29 Jose Gallego-Posada , Juan Ramirez , Akram Erraqabi , Yoshua Bengio , Simon Lacoste-Julien

Deep neural networks achieve state-of-the-art results on several tasks while increasing in complexity. It has been shown that neural networks can be pruned during training by imposing sparsity inducing regularizers. In this paper, we…

Machine Learning · Statistics 2019-08-12 Chaithanya Kumar Mummadi , Tim Genewein , Dan Zhang , Thomas Brox , Volker Fischer

Differentially private stochastic gradient descent (DP-SGD) has been widely adopted in deep learning to provide rigorously defined privacy, which requires gradient clipping to bound the maximum norm of individual gradients and additive…

Machine Learning · Computer Science 2023-06-29 Junyi Zhu , Matthew B. Blaschko

Recent theoretical studies proved that deep neural network (DNN) estimators obtained by minimizing empirical risk with a certain sparsity constraint can attain optimal convergence rates for regression and classification problems. However,…

Statistics Theory · Mathematics 2021-08-10 Ilsang Ohn , Yongdai Kim

Stochastic gradient descent (SGD) is a widely adopted iterative method for optimizing differentiable objective functions. In this paper, we propose and discuss a novel approach to scale up SGD in applications involving non-convex functions…

Machine Learning · Statistics 2022-10-07 Saad Mohamad , Hamad Alamri , Abdelhamid Bouchachia

Sparse regularization techniques are well-established in machine learning, yet their application in neural networks remains challenging due to the non-differentiability of penalties like the $L_1$ norm, which is incompatible with stochastic…

Machine Learning · Computer Science 2025-02-10 Chris Kolb , Tobias Weber , Bernd Bischl , David Rügamer

We study the problem of learning high dimensional regression models regularized by a structured-sparsity-inducing penalty that encodes prior structural information on either input or output sides. We consider two widely adopted types of…

Machine Learning · Computer Science 2012-02-20 Xi Chen , Qihang Lin , Seyoung Kim , Jaime G. Carbonell , Eric P. Xing

We propose to minimize a generic differentiable objective with $L_1$ constraint using a simple reparametrization and straightforward stochastic gradient descent. Our proposal is the direct generalization of previous ideas that the $L_1$…

Machine Learning · Computer Science 2023-07-13 Liu Ziyin , Zihao Wang

Minimizing a convex function of a measure with a sparsity-inducing penalty is a typical problem arising, e.g., in sparse spikes deconvolution or two-layer neural networks training. We show that this problem can be solved by discretizing the…

Optimization and Control · Mathematics 2020-11-04 Lenaic Chizat

Neural networks are easier to optimise when they have many more weights than are required for modelling the mapping from inputs to outputs. This suggests a two-stage learning procedure that first learns a large net and then prunes away…

Machine Learning · Computer Science 2019-09-10 Aidan N. Gomez , Ivan Zhang , Siddhartha Rao Kamalakara , Divyam Madaan , Kevin Swersky , Yarin Gal , Geoffrey E. Hinton

We propose precision gating (PG), an end-to-end trainable dynamic dual-precision quantization technique for deep neural networks. PG computes most features in a low precision and only a small proportion of important features in a higher…

Computer Vision and Pattern Recognition · Computer Science 2020-06-01 Yichi Zhang , Ritchie Zhao , Weizhe Hua , Nayun Xu , G. Edward Suh , Zhiru Zhang

We propose a practical method for $L_0$ norm regularization for neural networks: pruning the network during training by encouraging weights to become exactly zero. Such regularization is interesting since (1) it can greatly speed up…

Machine Learning · Statistics 2018-06-25 Christos Louizos , Max Welling , Diederik P. Kingma

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

This paper investigates a new learning formulation called structured sparsity, which is a natural extension of the standard sparsity concept in statistical learning and compressive sensing. By allowing arbitrary structures on the feature…

Methodology · Statistics 2009-05-05 Junzhou Huang , Tong Zhang , Dimitris Metaxas
‹ Prev 1 2 3 10 Next ›