English
Related papers

Related papers: Second-order Neural Network Training Using Complex…

200 papers

The known Complex Step Derivative (CSD) method allows easy and accurate differentiation up to machine precision of real analytic functions by evaluating them a small imaginary step next to the real number line. The current paper proposes…

Numerical Analysis · Mathematics 2021-06-18 Martin Roelfs , David Dudal , Daan Huybrechs

Gradient descent is the primary workhorse for optimizing large-scale problems in machine learning. However, its performance is highly sensitive to the choice of the learning rate. A key limitation of gradient descent is its lack of natural…

Optimization and Control · Mathematics 2025-07-15 Oscar Smee , Fred Roosta , Stephen J. Wright

A sequential training method for large-scale feedforward neural networks is presented. Each layer of the neural network is decoupled and trained separately. After the training is completed for each layer, they are combined together. The…

Machine Learning · Computer Science 2019-05-21 Jongrae Kim

In this paper, we consider both first- and second-order techniques to address continuous optimization problems arising in machine learning. In the first-order case, we propose a framework of transition from deterministic or…

Machine Learning · Computer Science 2021-11-30 Sanae Lotfi , Tiphaine Bonniot de Ruisselet , Dominique Orban , Andrea Lodi

This work proposes neural training as a \emph{process tensor}: a multi-time map that takes a sequence of controllable instruments (batch choices, augmentations, optimizer micro-steps) and returns an observable of the trained model. Building…

Machine Learning · Computer Science 2026-01-26 Vasileios Sevetlidis , George Pavlidis

By lifting the ReLU function into a higher dimensional space, we develop a smooth multi-convex formulation for training feed-forward deep neural networks (DNNs). This allows us to develop a block coordinate descent (BCD) training algorithm…

Machine Learning · Statistics 2017-11-21 Ziming Zhang , Matthew Brand

Data plays a pivotal role in the groundbreaking advancements in artificial intelligence. The quantitative analysis of data significantly contributes to model training, enhancing both the efficiency and quality of data utilization. However,…

Machine Learning · Computer Science 2025-08-21 Haoru Tan , Sitong Wu , Xiuzhe Wu , Wang Wang , Bo Zhao , Zeke Xie , Gui-Song Xia , Xiaojuan Qi

The massive size of modern neural networks has motivated substantial recent interest in neural network quantization. We introduce Stochastic Markov Gradient Descent (SMGD), a discrete optimization method applicable to training quantized…

Machine Learning · Computer Science 2020-12-23 Jonathan Ashbrock , Alexander M. Powell

Machine learning problems such as neural network training, tensor decomposition, and matrix factorization, require local minimization of a nonconvex function. This local minimization is challenged by the presence of saddle points, of which…

Optimization and Control · Mathematics 2018-07-23 Santiago Paternain , Aryan Mokhtari , Alejandro Ribeiro

First-order optimization methods are currently the mainstream in training deep neural networks (DNNs). Optimizers like Adam incorporate limited curvature information by employing the diagonal matrix preconditioning of the stochastic…

Machine Learning · Computer Science 2025-03-12 Damien Martins Gomes , Yanlei Zhang , Eugene Belilovsky , Guy Wolf , Mahdi S. Hosseini

In this paper, we study a second-order approach to policy optimization in reinforcement learning. Existing second-order methods often suffer from suboptimal sample complexity or rely on unrealistic assumptions about importance sampling. To…

Machine Learning · Computer Science 2025-07-15 Cheng Sun , Zhen Zhang , Shaofu Yang

Inspired by recent work of Islamov et al (2021), we propose a family of Federated Newton Learn (FedNL) methods, which we believe is a marked step in the direction of making second-order methods applicable to FL. In contrast to the…

Machine Learning · Computer Science 2022-05-24 Mher Safaryan , Rustem Islamov , Xun Qian , Peter Richtárik

In this paper, we propose a novel optimization algorithm for training machine learning models called Input Normalized Stochastic Gradient Descent (INSGD), inspired by the Normalized Least Mean Squares (NLMS) algorithm used in adaptive…

Machine Learning · Computer Science 2023-06-28 Salih Atici , Hongyi Pan , Ahmet Enis Cetin

State-of-the-art training algorithms for deep learning models are based on stochastic gradient descent (SGD). Recently, many variations have been explored: perturbing parameters for better accuracy (such as in Extragradient), limiting SGD…

Machine Learning · Computer Science 2022-03-23 Amirkeivan Mohtashami , Martin Jaggi , Sebastian U. Stich

This paper addresses the study of a new class of nonsmooth optimization problems, where the objective is represented as a difference of two generally nonconvex functions. We propose and develop a novel Newton-type algorithm to solving such…

Optimization and Control · Mathematics 2023-01-10 Francisco J. Aragón-Artacho , Boris S. Mordukhovich , Pedro Pérez-Aros

Bilevel optimization has arisen as a powerful tool in modern machine learning. However, due to the nested structure of bilevel optimization, even gradient-based methods require second-order derivative approximations via Jacobian- or/and…

Machine Learning · Computer Science 2022-06-07 Daouda Sow , Kaiyi Ji , Yingbin Liang

Multidimensional recurrent neural networks (MDRNNs) have shown a remarkable performance in the area of speech and handwriting recognition. The performance of an MDRNN is improved by further increasing its depth, and the difficulty of…

Machine Learning · Computer Science 2015-10-26 Minhyung Cho , Chandra Shekhar Dhir , Jaehyung Lee

We propose methodologies to train highly accurate and efficient deep convolutional neural networks (CNNs) for image super resolution (SR). A cascade training approach to deep learning is proposed to improve the accuracy of the neural…

Computer Vision and Pattern Recognition · Computer Science 2017-11-15 Haoyu Ren , Mostafa El-Khamy , Jungwon Lee

We present a coupled system of ODEs which, when discretized with a constant time step/learning rate, recovers Nesterov's accelerated gradient descent algorithm. The same ODEs, when discretized with a decreasing learning rate, leads to novel…

Optimization and Control · Mathematics 2020-09-02 Maxime Laborde , Adam M. Oberman

The minimization of the loss function is of paramount importance in deep neural networks. On the other hand, many popular optimization algorithms have been shown to correspond to some evolution equation of gradient flow type. Inspired by…

Machine Learning · Computer Science 2020-02-24 Imen Ayadi , Gabriel Turinici
‹ Prev 1 8 9 10 Next ›