English
Related papers

Related papers: Gradient Descent on Neurons and its Link to Approx…

200 papers

Second-order optimizers can significantly accelerate large-scale training, yet their naive federated variants are often unstable or even diverge on non-IID data. We show that a key culprit is \emph{preconditioner drift}: client-side…

Machine Learning · Computer Science 2026-02-24 Junkang Liu , Fanhua Shang , Hongying Liu , Jin Liu , Weixin An , Yuanyuan Liu

Neural collapse (NC) refers to the surprising structure of the last layer of deep neural networks in the terminal phase of gradient descent training. Recently, an increasing amount of experimental evidence has pointed to the propagation of…

Machine Learning · Computer Science 2023-05-23 Peter Súkeník , Marco Mondelli , Christoph Lampert

This paper proposes a novel approach to improve the training efficiency and the generalization performance of Feed Forward Neural Networks (FFNNs) resorting to an optimal rescaling of input features (OFR) carried out by a Genetic Algorithm…

Machine Learning · Computer Science 2024-02-21 Federico Maria Vitrò , Marco Leonesio , Lorenzo Fagiano

We present a new accelerated stochastic second-order method that is robust to both gradient and Hessian inexactness, which occurs typically in machine learning. We establish theoretical lower bounds and prove that our algorithm achieves…

Optimization and Control · Mathematics 2024-05-28 Artem Agafonov , Dmitry Kamzolov , Alexander Gasnikov , Ali Kavis , Kimon Antonakopoulos , Volkan Cevher , Martin Takáč

Two aspects of neural networks that have been extensively studied in the recent literature are their function approximation properties and their training by gradient descent methods. The approximation problem seeks accurate approximations…

Machine Learning · Computer Science 2022-09-20 R. Gentile , G. Welper

We present a novel approach to neural response prediction that incorporates higher-order operations directly within convolutional neural networks (CNNs). Our model extends traditional 3D CNNs by embedding higher-order operations within the…

Computer Vision and Pattern Recognition · Computer Science 2025-05-13 Simone Azeglio , Victor Calbiague Garcia , Guilhem Glaziou , Peter Neri , Olivier Marre , Ulisse Ferrari

First-order methods for solving convex optimization problems have been at the forefront of mathematical optimization in the last 20 years. The rapid development of this important class of algorithms is motivated by the success stories…

Optimization and Control · Mathematics 2021-01-07 Pavel Dvurechensky , Mathias Staudigl , Shimrit Shtern

Gradient descent methods have long been the de facto standard for training deep neural networks. Millions of training samples are fed into models with billions of parameters, which are slowly updated over hundreds of epochs. Recently, it's…

Machine Learning · Computer Science 2023-02-14 Tim Whitaker

Leveraging second-order information about the loss at the scale of deep networks is one of the main lines of approach for improving the performance of current optimizers for deep learning. Yet, existing approaches for accurate full-matrix…

Machine Learning · Computer Science 2024-06-06 Ionut-Vlad Modoranu , Aleksei Kalinov , Eldar Kurtic , Elias Frantar , Dan Alistarh

Over the past two decades, the feedforward neural network (FNN) optimization has been a key interest among the researchers and practitioners of multiple disciplines. The FNN optimization is often viewed from the various perspectives: the…

Neural and Evolutionary Computing · Computer Science 2017-05-17 Varun Kumar Ojha , Ajith Abraham , Václav Snášel

Building on our prior explorations of convolutional neural networks (CNNs) for financial data processing, this paper introduces two significant enhancements to refine our CNN model's predictive performance and robustness for financial…

Computational Finance · Quantitative Finance 2024-08-23 Sina Montazeri , Haseebullah Jumakhan , Sonia Abrasiabian , Amir Mirzaeinia

Natural gradient descent is an optimization method traditionally motivated from the perspective of information geometry, and works well for many applications as an alternative to stochastic gradient descent. In this paper we critically…

Machine Learning · Computer Science 2020-09-22 James Martens

Variational Bayesian neural networks combine the flexibility of deep learning with Bayesian uncertainty estimation. However, inference procedures for flexible variational posteriors are computationally expensive. A recently proposed method,…

Machine Learning · Computer Science 2018-12-03 Juhan Bae , Guodong Zhang , Roger Grosse

Coordinate networks are widely used in computer vision due to their ability to represent signals as compressed, continuous entities. However, training these networks with first-order optimizers can be slow, hindering their use in real-time…

Computer Vision and Pattern Recognition · Computer Science 2023-05-16 Hemanth Saratchandran , Shin-Fang Chng , Sameera Ramasinghe , Lachlan MacDonald , Simon Lucey

We study the training dynamics of gradient descent in a softmax self-attention layer trained to perform linear regression and show that a simple first-order optimization algorithm can converge to the globally optimal self-attention…

Machine Learning · Computer Science 2026-03-03 Gautam Goel , Mahdi Soltanolkotabi , Peter Bartlett

Differentiable simulators promise faster computation time for reinforcement learning by replacing zeroth-order gradient estimates of a stochastic objective with an estimate based on first-order gradients. However, it is yet unclear what…

Machine Learning · Computer Science 2022-08-23 H. J. Terry Suh , Max Simchowitz , Kaiqing Zhang , Russ Tedrake

Motivated by the potential for parallel implementation of batch-based algorithms and the accelerated convergence achievable with approximated second order information a limited memory version of the BFGS algorithm has been receiving…

Machine Learning · Computer Science 2023-03-07 Federico Zocco , Seán McLoone

The study of first-order optimization algorithms (FOA) typically starts with assumptions on the objective functions, most commonly smoothness and strong convexity. These metrics are used to tune the hyperparameters of FOA. We introduce a…

Machine Learning · Computer Science 2024-05-30 Charles Guille-Escuret , Baptiste Goujaud , Manuela Girotti , Ioannis Mitliagkas

In this paper, we present CT-AGD (Curvature-Tuned Accelerated Gradient Descent), an optimization method for non-convex optimization problems in deep learning training tasks. CT-AGD is a general boosting procedure that accelerates…

Machine Learning · Computer Science 2026-05-18 Manuel Graca , L. Miguel Silveira , Arlindo Oliveira , Frank Liu

We study the first-order convex optimization problem, where we have black-box access to a (not necessarily smooth) function $f:\mathbb{R}^n \to \mathbb{R}$ and its (sub)gradient. Our goal is to find an $\epsilon$-approximate minimum of $f$…

Data Structures and Algorithms · Computer Science 2020-10-06 Ankit Garg , Robin Kothari , Praneeth Netrapalli , Suhail Sherif
‹ Prev 1 8 9 10 Next ›