English
Related papers

Related papers: Neural gradients are near-lognormal: improved quan…

200 papers

While it is commonly observed in practice that pruning networks to a certain level of sparsity can improve the quality of the features, a theoretical explanation of this phenomenon remains elusive. In this work, we investigate this by…

Machine Learning · Statistics 2024-06-14 Nuri Mert Vural , Murat A. Erdogdu

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

Fully quantized training (FQT) accelerates the training of deep neural networks by quantizing the activations, weights, and gradients into lower precision. To explore the ultimate limit of FQT (the lowest achievable precision), we make a…

Machine Learning · Computer Science 2024-08-27 Chang Gao , Jianfei Chen , Kang Zhao , Jiaqi Wang , Liping Jing

Network quantization generally converts full-precision weights and/or activations into low-bit fixed-point values in order to accelerate an inference process. Recent approaches to network quantization further discretize the gradients into…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Dohyung Kim , Junghyup Lee , Jeimin Jeon , Jaehyeon Moon , Bumsub Ham

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

Researches have demonstrated that low bit-width (e.g., INT8) quantization can be employed to accelerate the inference process. It makes the gradient quantization very promising since the backward propagation requires approximately twice…

Computer Vision and Pattern Recognition · Computer Science 2021-02-10 Kang Zhao , Sida Huang , Pan Pan , Yinghan Li , Yingya Zhang , Zhenyu Gu , Yinghui Xu

As real-world graphs expand in size, larger GNN models with billions of parameters are deployed. High parameter count in such models makes training and inference on graphs expensive and challenging. To reduce the computational and memory…

Machine Learning · Computer Science 2023-02-27 Hongwu Peng , Deniz Gurevin , Shaoyi Huang , Tong Geng , Weiwen Jiang , Omer Khan , Caiwen Ding

Despite impressive performance, deep neural networks require significant memory and computation costs, prohibiting their application in resource-constrained scenarios. Sparse training is one of the most common techniques to reduce these…

Machine Learning · Computer Science 2023-12-06 Bowen Lei , Dongkuan Xu , Ruqi Zhang , Shuren He , Bani K. Mallick

Due to their high computational complexity, deep neural networks are still limited to powerful processing units. To promote a reduced model complexity by dint of low-bit fixed-point quantization, we propose a gradient-based optimization…

Machine Learning · Computer Science 2019-07-18 Lukas Enderich , Fabian Timm , Lars Rosenbaum , Wolfram Burgard

Proper regularization is critical for speeding up training, improving generalization performance, and learning compact models that are cost efficient. We propose and analyze regularized gradient descent algorithms for learning shallow…

Machine Learning · Computer Science 2018-06-08 Samet Oymak

The high computational complexity associated with training deep neural networks limits online and real-time training on edge devices. This paper proposed an end-to-end training and inference scheme that eliminates multiplications by…

Machine Learning · Computer Science 2026-05-05 Arnab Sanyal , Peter A. Beerel , Keith M. Chugg

Gradients of neural networks encode valuable information for optimization, editing, and analysis of models. Therefore, practitioners often treat gradients as inputs to task-specific algorithms, e.g. for pruning or optimization. Recent works…

Machine Learning · Computer Science 2025-10-14 Yoav Gelberg , Yam Eitan , Aviv Navon , Aviv Shamsian , Theo , Putterman , Michael Bronstein , Haggai Maron

Stochastic neurons can be useful for a number of reasons in deep learning models, but in many cases they pose a challenging problem: how to estimate the gradient of a loss function with respect to the input of such stochastic neurons, i.e.,…

Machine Learning · Computer Science 2013-05-15 Yoshua Bengio

Training deep neural networks on large datasets containing high-dimensional data requires a large amount of computation. A solution to this problem is data-parallel distributed training, where a model is replicated into several…

Machine Learning · Computer Science 2021-03-18 Lusine Abrahamyan , Yiming Chen , Giannis Bekoulis , Nikos Deligiannis

Due to the significant computational challenge of training large-scale graph neural networks (GNNs), various sparse learning techniques have been exploited to reduce memory and storage costs. Examples include \textit{graph sparsification}…

Machine Learning · Computer Science 2023-02-07 Shuai Zhang , Meng Wang , Pin-Yu Chen , Sijia Liu , Songtao Lu , Miao Liu

Neural networks are trained primarily based on their inputs and outputs, without regard for their internal mechanisms. These neglected mechanisms determine properties that are critical for safety, like (i) transparency; (ii) the absence of…

Machine Learning · Computer Science 2024-12-02 Alex Cloud , Jacob Goldman-Wetzler , Evžen Wybitul , Joseph Miller , Alexander Matt Turner

The general perception is that kernel methods are not scalable, and neural nets are the methods of choice for nonlinear learning problems. Or have we simply not tried hard enough for kernel methods? Here we propose an approach that scales…

Machine Learning · Computer Science 2015-09-11 Bo Dai , Bo Xie , Niao He , Yingyu Liang , Anant Raj , Maria-Florina Balcan , Le Song

We introduce a quantization-aware training algorithm that guarantees avoiding numerical overflow when reducing the precision of accumulators during inference. We leverage weight normalization as a means of constraining parameters during…

Machine Learning · Computer Science 2023-02-01 Ian Colbert , Alessandro Pappalardo , Jakoba Petri-Koenig

Quantized deep neural networks (QDNNs) are attractive due to their much lower memory storage and faster inference speed than their regular full precision counterparts. To maintain the same performance level especially at low bit-widths,…

Machine Learning · Computer Science 2019-01-08 Penghang Yin , Shuai Zhang , Jiancheng Lyu , Stanley Osher , Yingyong Qi , Jack Xin

The gradients used to train neural networks are typically computed using backpropagation. While an efficient way to obtain exact gradients, backpropagation is computationally expensive, hinders parallelization, and is biologically…

Machine Learning · Computer Science 2026-01-14 Katharina Flügel , Daniel Coquelin , Marie Weiel , Charlotte Debus , Achim Streit , Markus Götz