English
Related papers

Related papers: Computation of Generalized Derivatives for Abs-Smo…

200 papers

Stochastic gradient descent (SGD) is a standard optimization method to minimize a training error with respect to network parameters in modern neural network learning. However, it typically suffers from proliferation of saddle points in the…

Machine Learning · Computer Science 2017-11-23 Haiping Huang , Taro Toyoizumi

In this paper, we study efficient differentially private alternating direction methods of multipliers (ADMM) via gradient perturbation for many machine learning problems. For smooth convex loss functions with (non)-smooth regularization, we…

Machine Learning · Computer Science 2020-11-03 Tao Xu , Fanhua Shang , Yuanyuan Liu , Hongying Liu , Longjie Shen , Maoguo Gong

Conventional research attributes the improvements of generalization ability of deep neural networks either to powerful optimizers or the new network design. Different from them, in this paper, we aim to link the generalization ability of a…

Machine Learning · Computer Science 2018-11-06 Hui-Ling Zhen , Xi Lin , Alan Z. Tang , Zhenhua Li , Qingfu Zhang , Sam Kwong

In this work, multi-variable derivative-free optimization algorithms for unconstrained optimization problems are developed. A novel procedure for approximating the gradient of multi-variable objective functions based on non-commutative maps…

Optimization and Control · Mathematics 2021-11-17 Jan Feiling , Mohamed-Ali Belabbas , Christian Ebenbauer

Estimating hyperparameters has been a long-standing problem in machine learning. We consider the case where the task at hand is modeled as the solution to an optimization problem. Here the exact gradient with respect to the hyperparameters…

Optimization and Control · Mathematics 2023-11-16 Matthias J. Ehrhardt , Lindon Roberts

Stochastic gradient descent (SGD) performed in an asynchronous manner plays a crucial role in training large-scale machine learning models. However, the generalization performance of asynchronous delayed SGD, which is an essential metric…

Machine Learning · Computer Science 2025-05-27 Xiaoge Deng , Li Shen , Shengwei Li , Tao Sun , Dongsheng Li , Dacheng Tao

Out-of-distribution (OOD) detection is crucial for ensuring the reliability of deep learning models in real-world applications. Existing methods typically focus on feature representations or output-space analysis, often assuming a…

Computer Vision and Pattern Recognition · Computer Science 2025-09-18 Mostafa ElAraby , Sabyasachi Sahoo , Yann Pequignot , Paul Novello , Liam Paull

Adversarial learning methods are a promising approach to training robust deep networks, and can generate complex samples across diverse domains. They also can improve recognition despite the presence of domain shift or dataset bias: several…

Computer Vision and Pattern Recognition · Computer Science 2017-02-20 Eric Tzeng , Judy Hoffman , Kate Saenko , Trevor Darrell

Stochastic Gradient Descent (SGD) and its variants are the most used algorithms in machine learning applications. In particular, SGD with adaptive learning rates and momentum is the industry standard to train deep networks. Despite the…

Machine Learning · Statistics 2020-07-29 Xiaoyu Li , Francesco Orabona

Accurate diagnosis and prognosis of Alzheimer's disease are crucial to develop new therapies and reduce the associated costs. Recently, with the advances of convolutional neural networks, methods have been proposed to automate these two…

Image and Video Processing · Electrical Eng. & Systems 2022-11-29 Huy-Dung Nguyen , Michaël Clément , Boris Mansencal , Pierrick Coupé

Deep neural networks (DNNs) usually fail to generalize well to outside of distribution (OOD) data, especially in the extreme case of single domain generalization (single-DG) that transfers DNNs from single domain to multiple unseen domains.…

Computer Vision and Pattern Recognition · Computer Science 2023-03-14 Sanqing Qu , Yingwei Pan , Guang Chen , Ting Yao , Changjun Jiang , Tao Mei

The training of artificial neural networks (ANNs) with rectified linear unit (ReLU) activation via gradient descent (GD) type optimization schemes is nowadays a common industrially relevant procedure. Till this day in the scientific…

Machine Learning · Computer Science 2023-04-13 Simon Eberle , Arnulf Jentzen , Adrian Riekert , Georg S. Weiss

Machine unlearning algorithms aim to remove the impact of selected training data from a model without the computational expenses of retraining from scratch. Two such algorithms are ``Descent-to-Delete" (D2D) and ``Rewind-to-Delete" (R2D),…

Machine Learning · Computer Science 2026-03-02 Siqiao Mu , Diego Klabjan

The stochastic gradient descent (SGD) method and its variants are algorithms of choice for many Deep Learning tasks. These methods operate in a small-batch regime wherein a fraction of the training data, say $32$-$512$ data points, is…

Machine Learning · Computer Science 2017-02-13 Nitish Shirish Keskar , Dheevatsa Mudigere , Jorge Nocedal , Mikhail Smelyanskiy , Ping Tak Peter Tang

In this work we systematically analyze general properties of differential equations used as machine learning models. We demonstrate that the gradient of the loss function with respect to to the hidden state can be considered as a…

Machine Learning · Statistics 2019-10-30 Julius Ruseckas

A number of results have recently demonstrated the benefits of incorporating various constraints when training deep architectures in vision and machine learning. The advantages range from guarantees for statistical generalization to better…

Machine Learning · Computer Science 2019-05-27 Sathya N. Ravi , Tuan Dinh , Vishnu Lokhande , Vikas Singh

This paper considers non-smooth optimization problems where we seek to minimize the pointwise maximum of a continuously parameterized family of functions. Since the objective function is given as the solution to a maximization problem,…

Optimization and Control · Mathematics 2026-01-12 Dimitris Boskos , Jorge Cortés , Sonia Martínez

In this paper, we focus on the decentralized stochastic subgradient-based methods in minimizing nonsmooth nonconvex functions without Clarke regularity, especially in the decentralized training of nonsmooth neural networks. We propose a…

Optimization and Control · Mathematics 2026-01-07 Siyuan Zhang , Nachuan Xiao , Xin Liu

The explication of Convolutional Neural Networks (CNN) through xAI techniques often poses challenges in interpretation. The inherent complexity of input features, notably pixels extracted from images, engenders complex correlations.…

Computer Vision and Pattern Recognition · Computer Science 2024-05-16 Caroline Mazini Rodrigues , Nicolas Boutry , Laurent Najman

Gradient descent optimization algorithms are the standard ingredients that are used to train artificial neural networks (ANNs). Even though a huge number of numerical simulations indicate that gradient descent optimization methods do indeed…

Numerical Analysis · Mathematics 2022-02-04 Patrick Cheridito , Arnulf Jentzen , Adrian Riekert , Florian Rossmannek