English
Related papers

Related papers: Initialization and Regularization of Factorized Ne…

200 papers

Works on implicit regularization have studied gradient trajectories during the optimization process to explain why deep networks favor certain kinds of solutions over others. In deep linear networks, it has been shown that gradient descent…

Machine Learning · Computer Science 2023-06-02 Dan Zhao

Efforts to understand the generalization mystery in deep learning have led to the belief that gradient-based optimization induces a form of implicit regularization, a bias towards models of low "complexity." We study the implicit…

Machine Learning · Computer Science 2019-10-29 Sanjeev Arora , Nadav Cohen , Wei Hu , Yuping Luo

The overfitting is one of the cursing subjects in the deep learning field. To solve this challenge, many approaches were proposed to regularize the learning models. They add some hyper-parameters to the model to extend the generalization;…

Machine Learning · Computer Science 2020-05-06 Mohammad Mahdi Bejani , Mehdi Ghatee

Recurrent Neural Networks (RNNs) can be seriously impacted by the initial parameters assignment, which may result in poor generalization performances on new unseen data. With the objective to tackle this crucial issue, in the context of RNN…

Machine Learning · Computer Science 2019-11-05 Dino Ienco , Roberto Interdonato , Raffaele Gaetano

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

Word-embeddings are vital components of Natural Language Processing (NLP) models and have been extensively explored. However, they consume a lot of memory which poses a challenge for edge deployment. Embedding matrices, typically, contain…

Computation and Language · Computer Science 2020-11-12 Vasileios Lioutas , Ahmad Rashid , Krtin Kumar , Md Akmal Haidar , Mehdi Rezagholizadeh

The successes of intelligent systems have quite relied on the artificial learning of information, which lead to the broad applications of neural learning solutions. As a common sense, the training of neural networks can be largely improved…

Machine Learning · Computer Science 2025-04-15 Miao Cheng , Feiyan Zhou , Hongwei Zou , Limin Wang

We construct custom regularization functions for use in supervised training of deep neural networks. Our technique is applicable when the ground-truth labels themselves exhibit internal structure; we derive a regularizer by learning an…

Computer Vision and Pattern Recognition · Computer Science 2018-04-09 Mohammadreza Mostajabi , Michael Maire , Gregory Shakhnarovich

Tensor decomposition is one of the fundamental technique for model compression of deep convolution neural networks owing to its ability to reveal the latent relations among complex structures. However, most existing methods compress the…

Computer Vision and Pattern Recognition · Computer Science 2021-12-08 Bo-Shiuan Chu , Che-Rung Lee

It has been observed in practice that applying pruning-at-initialization methods to neural networks and training the sparsified networks can not only retain the testing performance of the original dense models, but also sometimes even…

Machine Learning · Computer Science 2023-01-31 Hongru Yang , Yingbin Liang , Xiaojie Guo , Lingfei Wu , Zhangyang Wang

Deep feedforward neural networks with piecewise linear activations are currently producing the state-of-the-art results in several public datasets. The combination of deep learning models and piecewise linear activation functions allows for…

Computer Vision and Pattern Recognition · Computer Science 2015-11-03 Zhibin Liao , Gustavo Carneiro

Despite Deep Learning's (DL) empirical success, our theoretical understanding of its efficacy remains limited. One notable paradox is that while conventional wisdom discourages perfect data fitting, deep neural networks are designed to do…

Machine Learning · Computer Science 2024-02-06 Oria Gruber , Haim Avron

The effect of regularizers such as weight decay when training deep neural networks is not well understood. We study the influence of weight decay as well as $L2$-regularization when training neural network models in which parameter matrices…

Machine Learning · Computer Science 2024-11-01 Seijin Kobayashi , Yassir Akram , Johannes Von Oswald

Training deep neural networks for scientific computing remains computationally expensive due to the slow formation of diverse feature representations in early training stages. Recent studies identify a staircase phenomenon in training…

Numerical Analysis · Mathematics 2025-07-17 Tao Tang , Jiang Yang , Yuxiang Zhao , Quanhui Zhu

Sparse neural networks are highly desirable in deep learning in reducing its complexity. The goal of this paper is to study how choices of regularization parameters influence the sparsity level of learned neural networks. We first derive…

Machine Learning · Computer Science 2024-08-07 Lixin Shen , Rui Wang , Yuesheng Xu , Mingsong Yan

The phenomenon of distinct behaviors exhibited by neural networks under varying scales of initialization remains an enigma in deep learning research. In this paper, based on the earlier work by Luo et al.~\cite{luo2021phase}, we present a…

Machine Learning · Computer Science 2026-04-02 Zhengan Chen , Yuqing Li , Tao Luo , Zhangchen Zhou , Zhi-Qin John Xu

In low-latency or mobile applications, lower computation complexity, lower memory footprint and better energy efficiency are desired. Many prior works address this need by removing redundant parameters. Parameter quantization replaces…

Machine Learning · Computer Science 2021-11-16 Cheng-Chou Lan

Training Deep Learning (DL) models require large, high-quality datasets, often assembled with data from different institutions. Federated Learning (FL) has been emerging as a method for privacy-preserving pooling of datasets employing…

Machine Learning · Computer Science 2023-03-21 Bruno Casella , Roberto Esposito , Antonio Sciarappa , Carlo Cavazzoni , Marco Aldinucci

Re-initializing a neural network during training has been observed to improve generalization in recent works. Yet it is neither widely adopted in deep learning practice nor is it often used in state-of-the-art training protocols. This…

Machine Learning · Computer Science 2023-04-04 Sheheryar Zaidi , Tudor Berariu , Hyunjik Kim , Jörg Bornschein , Claudia Clopath , Yee Whye Teh , Razvan Pascanu

Stochastic variational inference is an established way to carry out approximate Bayesian inference for deep models. While there have been effective proposals for good initializations for loss minimization in deep learning, far less…

Machine Learning · Statistics 2019-01-28 Simone Rossi , Pietro Michiardi , Maurizio Filippone