English
Related papers

Related papers: When, Where and Why to Average Weights?

200 papers

The largely successful method of training neural networks is to learn their weights using some variant of stochastic gradient descent (SGD). Here, we show that the solutions found by SGD can be further improved by ensembling a subset of the…

Continual learning poses a fundamental challenge for modern machine learning systems, requiring models to adapt to new tasks while retaining knowledge from previous ones. Addressing this challenge necessitates the development of efficient…

Machine Learning · Computer Science 2024-04-10 Jędrzej Kozal , Jan Wasilewski , Bartosz Krawczyk , Michał Woźniak

It is well known that building analytical performance models in practice is difficult because it requires a considerable degree of proficiency in the underlying mathematics. In this paper, we propose a machine-learning approach to derive…

Performance · Computer Science 2020-02-26 Giulio Garbi , Emilio Incerto , Mirco Tribastone

Recent observations have advanced our understanding of the neural network optimization landscape, revealing the existence of (1) paths of high accuracy containing diverse solutions and (2) wider minima offering improved performance.…

Machine Learning · Computer Science 2021-09-14 Mitchell Wortsman , Maxwell Horton , Carlos Guestrin , Ali Farhadi , Mohammad Rastegari

Mislabeled, duplicated, or biased data in real-world scenarios can lead to prolonged training and even hinder model convergence. Traditional solutions prioritizing easy or hard samples lack the flexibility to handle such a variety…

Machine Learning · Computer Science 2023-11-08 Zhijie Deng , Peng Cui , Jun Zhu

Training large-scale deep learning models has become a key challenge for the scientific community and industry. While the massive use of GPUs can significantly speed up training times, this approach has a negative impact on efficiency. In…

Machine Learning · Computer Science 2025-09-04 David Cortes , Carlos Juiz , Belen Bermejo

In this paper we propose to study generalization of neural networks on small algorithmically generated datasets. In this setting, questions about data efficiency, memorization, generalization, and speed of learning can be studied in great…

Machine Learning · Computer Science 2022-01-07 Alethea Power , Yuri Burda , Harri Edwards , Igor Babuschkin , Vedant Misra

Generalization of deep neural networks remains one of the main open problems in machine learning. Previous theoretical works focused on deriving tight bounds of model complexity, while empirical works revealed that neural networks exhibit…

Machine Learning · Computer Science 2022-01-31 James Wang , Cheng-Lin Yang

Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating…

Machine Learning · Computer Science 2017-08-22 Luke Taylor , Geoff Nitschke

Neural architecture search has attracted wide attentions in both academia and industry. To accelerate it, researchers proposed weight-sharing methods which first train a super-network to reuse computation among different operators, from…

Machine Learning · Computer Science 2020-12-16 Xin Chen , Lingxi Xie , Jun Wu , Longhui Wei , Yuhui Xu , Qi Tian

In this work, we present a general framework for continual learning of sequentially arrived tasks with the use of pre-training, which has emerged as a promising direction for artificial intelligence systems to accommodate real-world…

Machine Learning · Computer Science 2024-07-10 Liyuan Wang , Jingyi Xie , Xingxing Zhang , Hang Su , Jun Zhu

Deep learning is rapidly becoming a go-to tool for many artificial intelligence problems due to its ability to outperform other approaches and even humans at many problems. Despite its popularity we are still unable to accurately predict…

Machine Learning · Computer Science 2018-11-30 Daniel Justus , John Brennan , Stephen Bonner , Andrew Stephen McGough

Deep convolutional neural networks are known to be unstable during training at high learning rate unless normalization techniques are employed. Normalizing weights or activations allows the use of higher learning rates, resulting in faster…

Machine Learning · Computer Science 2019-12-02 Brendan Ruff , Taylor Beck , Joscha Bach

Adversarial training has been proven to be a powerful regularization method to improve the generalization of models. However, current adversarial training methods only attack the original input sample or the embedding vectors, and their…

Machine Learning · Computer Science 2021-08-31 Shiwen Ni , Jiawen Li , Hung-Yu Kao

We present weight normalization: a reparameterization of the weight vectors in a neural network that decouples the length of those weight vectors from their direction. By reparameterizing the weights in this way we improve the conditioning…

Machine Learning · Computer Science 2016-06-07 Tim Salimans , Diederik P. Kingma

This study proposes a method to enhance neural network performance when training data and application data are not very similar, e.g., out of distribution problems, as well as pattern and regime shifts. The method consists of three main…

Machine Learning · Computer Science 2025-12-04 Jan Saynisch-Wagner , Saran Rajendran Sari

Despite being widely adopted as a canonical framework for learning robust models, adversarial training suffers from robust overfitting. Existing empirical measures and theoretical explorations are insufficient to provide satisfying…

Machine Learning · Computer Science 2026-03-10 Yuelin Xu , Xiao Zhang

Continual learning is conventionally tackled through sequential fine-tuning, a process that, while enabling adaptation, inherently favors plasticity over the stability needed to retain prior knowledge. While existing approaches attempt to…

Computer Vision and Pattern Recognition · Computer Science 2025-06-05 Ghada Sokar , Gintare Karolina Dziugaite , Anurag Arnab , Ahmet Iscen , Pablo Samuel Castro , Cordelia Schmid

Modern deep models are often pretrained on large-scale data with missing labels using composite objectives, where the relative weights of multiple loss terms act as hyperparameters. Tuning these weights with random search or Bayesian…

Machine Learning · Computer Science 2026-05-11 Ivan Karpukhin , Andrey Savchenko

Contrary to most machine learning models, modern deep artificial neural networks typically include multiple components that contribute to regularization. Despite the fact that some (explicit) regularization techniques, such as weight decay…

Computer Vision and Pattern Recognition · Computer Science 2020-11-13 Alex Hernández-García , Peter König
‹ Prev 1 8 9 10 Next ›