English
Related papers

Related papers: Data Distributional Properties As Inductive Bias f…

200 papers

Distributed implementations of mini-batch stochastic gradient descent (SGD) suffer from communication overheads, attributed to the high frequency of gradient updates inherent in small-batch training. Training with large batches can reduce…

Machine Learning · Statistics 2018-06-12 Lingjiao Chen , Hongyi Wang , Jinman Zhao , Dimitris Papailiopoulos , Paraschos Koutris

Gaussian noise injections (GNIs) are a family of simple and widely-used regularisation methods for training neural networks, where one injects additive or multiplicative Gaussian noise to the network activations at every iteration of the…

Machine Learning · Statistics 2021-06-14 Alexander Camuto , Xiaoyu Wang , Lingjiong Zhu , Chris Holmes , Mert Gürbüzbalaban , Umut Şimşekli

Practitioners prune neural networks for efficiency gains and generalization improvements, but few scrutinize the factors determining the prunability of a neural network the maximum fraction of weights that pruning can remove without…

Machine Learning · Computer Science 2022-12-02 Zachary Ankner , Alex Renda , Gintare Karolina Dziugaite , Jonathan Frankle , Tian Jin

Learning tasks such as those involving genomic data often poses a serious challenge: the number of input features can be orders of magnitude larger than the number of training examples, making it difficult to avoid overfitting, even when…

In this paper, we first present an explanation regarding the common occurrence of spikes in the training loss when neural networks are trained with stochastic gradient descent (SGD). We provide evidence that the spikes in the training loss…

Machine Learning · Computer Science 2024-06-07 Libin Zhu , Chaoyue Liu , Adityanarayanan Radhakrishnan , Mikhail Belkin

A major challenge in understanding the generalization of deep learning is to explain why (stochastic) gradient descent can exploit the network architecture to find solutions that have good generalization performance when using high capacity…

Machine Learning · Computer Science 2019-02-12 Yifan Wu , Barnabas Poczos , Aarti Singh

Randomness is an unavoidable part of training deep learning models, yet something that traditional training data attribution algorithms fail to rigorously account for. They ignore the fact that, due to stochasticity in the initialisation…

Machine Learning · Computer Science 2025-10-28 Bruno Mlodozeniec , Isaac Reid , Sam Power , David Krueger , Murat Erdogdu , Richard E. Turner , Roger Grosse

Deep neural networks (DNNs) trained for image denoising are able to generate high-quality samples with score-based reverse diffusion algorithms. These impressive capabilities seem to imply an escape from the curse of dimensionality, but…

Computer Vision and Pattern Recognition · Computer Science 2025-03-03 Zahra Kadkhodaie , Florentin Guth , Eero P. Simoncelli , Stéphane Mallat

Deep neural networks (DNNs) are typically optimized using various forms of mini-batch gradient descent algorithm. A major motivation for mini-batch gradient descent is that with a suitably chosen batch size, available computing resources…

Machine Learning · Computer Science 2022-10-25 Oyebade K. Oyedotun , Konstantinos Papadopoulos , Djamila Aouada

Despite rapid progress in large language models (LLMs), the statistical structure of their weights, activations, and gradients-and its implications for initialization, training dynamics, and efficiency-remains largely unexplored. We…

Machine Learning · Computer Science 2026-02-24 Jun Wu , Patrick Huang , Jiangtao Wen , Yuxing Han

Domain invariant learning aims to learn models that extract invariant features over various training domains, resulting in better generalization to unseen target domains. Recently, Bayesian Neural Networks have achieved promising results in…

Machine Learning · Computer Science 2023-10-26 Shiyu Shen , Bin Pan , Tianyang Shi , Tao Li , Zhenwei Shi

We characterize the connectivity structure of feed-forward, deep neural networks (DNNs) using network motif theory. To address whether a particular motif distribution is characteristic of the training task, or function of the DNN, we…

Machine Learning · Computer Science 2024-03-05 Olivia T. Zahn , Thomas L. Daniel , J. Nathan Kutz

Deep neural networks (DNNs) often rely on massive labelled data for training, which is inaccessible in many applications. Data augmentation (DA) tackles data scarcity by creating new labelled data from available ones. Different DA methods…

Neural and Evolutionary Computing · Computer Science 2022-05-31 Binyan Hu , Yu Sun , A. K. Qin

Decentralized learning offers privacy and communication efficiency when data are naturally distributed among agents communicating over an underlying graph. Motivated by overparameterized learning settings, in which models are trained to…

Machine Learning · Computer Science 2023-03-28 Hossein Taheri , Christos Thrampoulidis

Though data augmentation has become a standard component of deep neural network training, the underlying mechanism behind the effectiveness of these techniques remains poorly understood. In practice, augmentation policies are often chosen…

Machine Learning · Computer Science 2020-06-08 Raphael Gontijo-Lopes , Sylvia J. Smullin , Ekin D. Cubuk , Ethan Dyer

Corrupting the input and hidden layers of deep neural networks (DNNs) with multiplicative noise, often drawn from the Bernoulli distribution (or 'dropout'), provides regularization that has significantly contributed to deep learning's…

Machine Learning · Statistics 2015-06-11 Eric Nalisnick , Anima Anandkumar , Padhraic Smyth

We describe an approach to understand the peculiar and counterintuitive generalization properties of deep neural networks. The approach involves going beyond worst-case theoretical capacity control frameworks that have been popular in…

Machine Learning · Computer Science 2019-02-19 Charles H. Martin , Michael W. Mahoney

Deep generative models (DGM) are neural networks with many hidden layers trained to approximate complicated, high-dimensional probability distributions using a large number of samples. When trained successfully, we can use the DGMs to…

Machine Learning · Computer Science 2021-04-13 Lars Ruthotto , Eldad Haber

In deep learning, neural networks serve as noisy channels between input data and its representation. This perspective naturally relates deep learning with the pursuit of constructing channels with optimal performance in information…

Machine Learning · Computer Science 2022-12-06 Kangyu Weng , Aohua Cheng , Ziyang Zhang , Pei Sun , Yang Tian

Speech enhancement using neural networks is recently receiving large attention in research and being integrated in commercial devices and applications. In this work, we investigate data augmentation techniques for supervised deep…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-25 Sebastian Braun , Ivan Tashev
‹ Prev 1 8 9 10 Next ›