English
Related papers

Related papers: Weak-SIGReg: Covariance Regularization for Stable …

200 papers

Deep generative models provide powerful tools for distributions over complicated manifolds, such as those of natural images. But many of these methods, including generative adversarial networks (GANs), can be difficult to train, in part…

Machine Learning · Statistics 2017-11-08 Akash Srivastava , Lazar Valkov , Chris Russell , Michael U. Gutmann , Charles Sutton

Classical machine learning models such as deep neural networks are usually trained by using Stochastic Gradient Descent-based (SGD) algorithms. The classical SGD can be interpreted as a discretization of the stochastic gradient flow. In…

Optimization and Control · Mathematics 2023-10-03 Valentin Leplat , Daniil Merkulov , Aleksandr Katrutsa , Daniel Bershatsky , Olga Tsymboi , Ivan Oseledets

Variance reduction (VR) methods employ stochastic gradients with decreasing variance, and they have been widely applied to solve large-scale optimization problems in machine learning because of their efficiency. Existing theoretical studies…

Machine Learning · Computer Science 2026-05-28 Yunwen Lei , Zimeng Wang , Xiaoming Yuan

We propose VISP: Volatility Informed Stochastic Projection, an adaptive regularization method that leverages gradient volatility to guide stochastic noise injection in deep neural networks. Unlike conventional techniques that apply uniform…

Machine Learning · Computer Science 2025-09-03 Tanvir Islam

Stochastic Gradient Descent (SGD) is a workhorse in machine learning, yet its slow convergence can be a computational bottleneck. Variance reduction techniques such as SAG, SVRG and SAGA have been proposed to overcome this weakness,…

Machine Learning · Computer Science 2016-02-29 Thomas Hofmann , Aurelien Lucchi , Simon Lacoste-Julien , Brian McWilliams

Stochastic variance reduced gradient (SVRG) is a popular variance reduction technique for accelerating stochastic gradient descent (SGD). We provide a first analysis of the method for solving a class of linear inverse problems in the lens…

Numerical Analysis · Mathematics 2022-01-19 Bangti Jin , Zehui Zhou , Jun Zou

Deep generative models based on Generative Adversarial Networks (GANs) have demonstrated impressive sample quality but in order to work they require a careful choice of architecture, parameter initialization, and selection of…

Machine Learning · Computer Science 2017-11-08 Kevin Roth , Aurelien Lucchi , Sebastian Nowozin , Thomas Hofmann

Deep neural networks have been shown to achieve state-of-the-art performance in several machine learning tasks. Stochastic Gradient Descent (SGD) is the preferred optimization algorithm for training these networks and asynchronous SGD…

Machine Learning · Computer Science 2016-04-06 Wei Zhang , Suyog Gupta , Xiangru Lian , Ji Liu

We introduce submodel co-training, a regularization method related to co-training, self-distillation and stochastic depth. Given a neural network to be trained, for each sample we implicitly instantiate two altered networks, ``submodels'',…

Computer Vision and Pattern Recognition · Computer Science 2022-12-12 Hugo Touvron , Matthieu Cord , Maxime Oquab , Piotr Bojanowski , Jakob Verbeek , Hervé Jégou

The transformer architecture has demonstrated strong performance in classification tasks involving structured and high-dimensional data. However, its success often hinges on large- scale training data and careful regularization to prevent…

Machine Learning · Statistics 2025-11-18 Mohamed Salem , Inyoung Kim

Video representation learning is an increasingly important topic in machine learning research. We present Video JEPA with Variance-Covariance Regularization (VJ-VCR): a joint-embedding predictive architecture for self-supervised video…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Katrina Drozdov , Ravid Shwartz-Ziv , Yann LeCun

Learning rate scheduling plays a critical role in the optimization of deep neural networks, directly influencing convergence speed, stability, and generalization. While existing schedulers such as cosine annealing, cyclical learning rates,…

Machine Learning · Computer Science 2026-03-05 Ayush K. Varshney , Šarūnas Girdzijauskas , Konstantinos Vandikas , Aneta Vulgarakis Feljan

In this paper we consider the training of single hidden layer neural networks by pseudoinversion, which, in spite of its popularity, is sometimes affected by numerical instability issues. Regularization is known to be effective in such…

Neural and Evolutionary Computing · Computer Science 2015-08-26 Rossella Cancelliere , Mario Gai , Patrick Gallinari , Luca Rubini

The application of stochastic variance reduction to optimization has shown remarkable recent theoretical and practical success. The applicability of these techniques to the hard non-convex optimization problems encountered during training…

Machine Learning · Computer Science 2019-11-21 Aaron Defazio , Léon Bottou

We propose a new regularization method to alleviate over-fitting in deep neural networks. The key idea is utilizing randomly transformed training samples to regularize a set of sub-networks, which are originated by sampling the width of the…

Computer Vision and Pattern Recognition · Computer Science 2020-10-14 Taojiannan Yang , Sijie Zhu , Chen Chen

Spiking neural networks are a promising approach towards next-generation models of the brain in computational neuroscience. Moreover, compared to classic artificial neural networks, they could serve as an energy-efficient deployment of AI…

Neural and Evolutionary Computing · Computer Science 2021-09-24 Justus F. Hübotter , Pablo Lanillos , Jakub M. Tomczak

The Vision Transformer architecture is a deep learning model inspired by the success of the Transformer model in Natural Language Processing. However, the self-attention mechanism, large number of parameters, and the requirement for a…

Computer Vision and Pattern Recognition · Computer Science 2023-07-25 Yogi Prasetyo , Novanto Yudistira , Agus Wahyu Widodo

Centralized training is the standard paradigm in deep learning, enabling models to learn from a unified dataset in a single location. In such setup, isotropic feature distributions naturally arise as a mean to support well-structured and…

Machine Learning · Computer Science 2026-02-09 Chiara Lanza , Roberto Pereira , Marco Miozzo , Eduard Angelats , Paolo Dini

Deep learning has emerged as a strong alternative for classical iterative methods for deformable medical image registration, where the goal is to find a mapping between the coordinate systems of two images. Popular classical image…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Joel Honkamaa , Pekka Marttinen

Machine learning models trained with \emph{stochastic} gradient descent (SGD) can generalize better than those trained with deterministic gradient descent (GD). In this work, we study SGD's impact on generalization through the lens of the…

Machine Learning · Computer Science 2025-12-09 Hongjian Lan , Yucong Liu , Florian Schäfer