English
Related papers

Related papers: Weight Conditioning for Smooth Optimization of Neu…

200 papers

Recently theoretical guarantees have been obtained for matrix completion in the non-uniform sampling regime. In particular, if the sampling distribution aligns with the underlying matrix's leverage scores, then with high probability nuclear…

Machine Learning · Statistics 2015-04-03 Jason Jo

A significant advance in accelerating neural network training has been the development of normalization methods, permitting the training of deep models both faster and with better accuracy. These advances come with practical challenges: for…

Machine Learning · Computer Science 2019-03-05 Jasmine Collins , Johannes Balle , Jonathon Shlens

We introduce a new technique for gradient normalization during neural network training. The gradients are rescaled during the backward pass using normalization layers introduced at certain points within the network architecture. These…

Machine Learning · Computer Science 2021-06-18 Alejandro Cabana , Luis F. Lago-Fernández

Batch normalization (BN) has become a de facto standard for training deep convolutional networks. However, BN accounts for a significant fraction of training run-time and is difficult to accelerate, since it is a memory-bandwidth bounded…

Computer Vision and Pattern Recognition · Computer Science 2017-10-10 Igor Gitman , Boris Ginsburg

Normalization layers (e.g., Batch Normalization, Layer Normalization) were introduced to help with optimization difficulties in very deep nets, but they clearly also help generalization, even in not-so-deep nets. Motivated by the long-held…

Machine Learning · Computer Science 2023-01-18 Kaifeng Lyu , Zhiyuan Li , Sanjeev Arora

We present a method to train self-binarizing neural networks, that is, networks that evolve their weights and activations during training to become binary. To obtain similar binary networks, existing methods rely on the sign activation…

Computer Vision and Pattern Recognition · Computer Science 2019-02-05 Fayez Lahoud , Radhakrishna Achanta , Pablo Márquez-Neila , Sabine Süsstrunk

Neural network algorithms simulated on standard computing platforms typically make use of high resolution weights, with floating-point notation. However, for dedicated hardware implementations of such algorithms, fixed-point synaptic…

Neural and Evolutionary Computing · Computer Science 2015-04-23 Lorenz K. Muller , Giacomo Indiveri

We investigate the generalizability of deep learning based on the sensitivity to input perturbation. We hypothesize that the high sensitivity to the perturbation of data degrades the performance on it. To reduce the sensitivity to…

Machine Learning · Statistics 2017-06-01 Yuichi Yoshida , Takeru Miyato

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

Despite recent algorithmic advances, we still lack principled ways to leverage the well-documented rescaling symmetries in ReLU neural network parameters. While two properly rescaled weights implement the same function, the training…

Machine Learning · Statistics 2026-02-24 Arthur Lebeurrier , Titouan Vayer , Rémi Gribonval

In this paper, we introduce a novel method of neural network weight compression. In our method, we store weight tensors as sparse, quantized matrix factors, whose product is computed on the fly during inference to generate the target…

Machine Learning · Computer Science 2022-07-25 Andrey Kuzmin , Mart van Baalen , Markus Nagel , Arash Behboodi

Weight initialization plays an important role in neural network training. Widely used initialization methods are proposed and evaluated for networks that are trained from scratch. However, the growing number of pretrained models now offers…

Machine Learning · Computer Science 2023-12-01 Zhiqiu Xu , Yanjie Chen , Kirill Vishniakov , Yida Yin , Zhiqiang Shen , Trevor Darrell , Lingjie Liu , Zhuang Liu

Deep learning has been wildly successful in practice and most state-of-the-art machine learning methods are based on neural networks. Lacking, however, is a rigorous mathematical theory that adequately explains the amazing performance of…

Machine Learning · Statistics 2023-10-03 Rahul Parhi , Robert D. Nowak

Weight sharing has become a de facto standard in neural architecture search because it enables the search to be done on commodity hardware. However, recent works have empirically shown a ranking disorder between the performance of…

Machine Learning · Computer Science 2021-04-13 Kaicheng Yu , Rene Ranftl , Mathieu Salzmann

Model regularization requires extensive manual tuning to balance complexity against overfitting. Cross-regularization resolves this tradeoff by directly adapting regularization parameters through validation gradients during training. The…

Machine Learning · Computer Science 2025-06-25 Carlos Stein Brito

This study investigates how weight decay affects the update behavior of individual neurons in deep neural networks through a combination of applied analysis and experimentation. Weight decay can cause the expected magnitude and angular…

Machine Learning · Computer Science 2024-06-04 Atli Kosson , Bettina Messmer , Martin Jaggi

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

In this work, we investigate the fundamental trade-off regarding accuracy and parameter efficiency in the parameterization of neural network weights using predictor networks. We present a surprising finding that, when recovering the…

Machine Learning · Computer Science 2024-07-02 Hongjun Choi , Jayaraman J. Thiagarajan , Ruben Glatt , Shusen Liu

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

Conditioning analysis uncovers the landscape of an optimization objective by exploring the spectrum of its curvature matrix. This has been well explored theoretically for linear models. We extend this analysis to deep neural networks (DNNs)…

Computer Vision and Pattern Recognition · Computer Science 2020-07-30 Lei Huang , Jie Qin , Li Liu , Fan Zhu , Ling Shao
‹ Prev 1 4 5 6 7 8 10 Next ›