English
Related papers

Related papers: Neural Nets with a Newton Conjugate Gradient Metho…

200 papers

Stochastic second-order methods achieve fast local convergence in strongly convex optimization by using noisy Hessian estimates to precondition the gradient. However, these methods typically reach superlinear convergence only when the…

Optimization and Control · Mathematics 2024-11-12 Ruichen Jiang , Michał Dereziński , Aryan Mokhtari

While first-order optimization methods such as stochastic gradient descent (SGD) are popular in machine learning (ML), they come with well-known deficiencies, including relatively-slow convergence, sensitivity to the settings of…

Optimization and Control · Mathematics 2018-02-19 Peng Xu , Farbod Roosta-Khorasani , Michael W. Mahoney

Many optimizers have been proposed for training deep neural networks, and they often have multiple hyperparameters, which make it tricky to benchmark their performance. In this work, we propose a new benchmarking protocol to evaluate both…

Machine Learning · Computer Science 2020-10-21 Yuanhao Xiong , Xuanqing Liu , Li-Cheng Lan , Yang You , Si Si , Cho-Jui Hsieh

We develop multi-step gradient methods for network-constrained optimization of strongly convex functions with Lipschitz-continuous gradients. Given the topology of the underlying network and bounds on the Hessian of the objective function,…

Optimization and Control · Mathematics 2015-06-12 Euhanna Ghadimi , Iman Shames , Mikael Johansson

Hyperparameter optimization can be formulated as a bilevel optimization problem, where the optimal parameters on the training set depend on the hyperparameters. We aim to adapt regularization hyperparameters for neural networks by fitting…

Machine Learning · Computer Science 2019-03-08 Matthew MacKay , Paul Vicol , Jon Lorraine , David Duvenaud , Roger Grosse

With the growing importance of large network models and enormous training datasets, GPUs have become increasingly necessary to train neural networks. This is largely because conventional optimization algorithms rely on stochastic gradient…

Machine Learning · Computer Science 2016-05-09 Gavin Taylor , Ryan Burmeister , Zheng Xu , Bharat Singh , Ankit Patel , Tom Goldstein

Training deep neural networks is a structured optimization problem, because the parameters are naturally represented by matrices and tensors rather than by vectors. Under this structural representation, it has been widely observed that…

Machine Learning · Computer Science 2025-10-30 Kang An , Yuxing Liu , Rui Pan , Yi Ren , Shiqian Ma , Donald Goldfarb , Tong Zhang

A class of second-order algorithms is proposed for minimizing smooth nonconvex functions that alternates between regularized Newton and negative curvature steps in an iteration-dependent subspace. In most cases, the Hessian matrix is…

Optimization and Control · Mathematics 2023-08-22 Serge Gratton , Sadok Jerad , Philippe L. Toint

While first-order methods are popular for solving optimization problems that arise in large-scale deep learning problems, they come with some acute deficiencies. To diminish such shortcomings, there has been recent interest in applying…

Machine Learning · Computer Science 2023-10-05 Mahsa Yousefi , Angeles Martinez

Neural networks often struggle with high-dimensional but small sample-size tabular datasets. One reason is that current weight initialisation methods assume independence between weights, which can be problematic when there are insufficient…

Machine Learning · Computer Science 2024-08-20 Andrei Margeloiu , Nikola Simidjievski , Pietro Lio , Mateja Jamnik

Most learning algorithms require the practitioner to manually set the values of many hyperparameters before the learning process can begin. However, with modern algorithms, the evaluation of a given hyperparameter setting can take a…

Neural and Evolutionary Computing · Computer Science 2018-07-20 Tobias Hinz , Nicolás Navarro-Guerrero , Sven Magg , Stefan Wermter

Gravitational-wave detection strategies are based on a signal analysis technique known as matched filtering. Despite the success of matched filtering, due to its computational cost, there has been recent interest in developing deep…

General Relativity and Quantum Cosmology · Physics 2022-11-03 Dwyer S. Deighan , Scott E. Field , Collin D. Capano , Gaurav Khanna

This paper presents an evolutionary metaheuristic called Multiple Search Neuroevolution (MSN) to optimize deep neural networks. The algorithm attempts to search multiple promising regions in the search space simultaneously, maintaining…

Neural and Evolutionary Computing · Computer Science 2019-01-21 Ahmed Aly , David Weikersdorfer , Claire Delaunay

This note explores the applicability of unsupervised machine learning techniques towards hard optimization problems on random inputs. In particular we consider Graph Neural Networks (GNNs) -- a class of neural networks designed to learn…

Optimization and Control · Mathematics 2019-08-19 Weichi Yao , Afonso S. Bandeira , Soledad Villar

Finite-sum optimization problems are ubiquitous in machine learning, and are commonly solved using first-order methods which rely on gradient computations. Recently, there has been growing interest in \emph{second-order} methods, which rely…

Optimization and Control · Mathematics 2017-03-09 Yossi Arjevani , Ohad Shamir

This paper considers distributed optimization problems, where each agent cooperatively minimizes the sum of local objective functions through the communication with its neighbors. The widely adopted distributed gradient method in solving…

Optimization and Control · Mathematics 2025-08-19 Yeming Xu , Ziyuan Guo , Kaihong Lu , Huanshui Zhang

The architecture and the parameters of neural networks are often optimized independently, which requires costly retraining of the parameters whenever the architecture is modified. In this work we instead focus on growing the architecture…

Machine Learning · Computer Science 2022-06-08 Utku Evci , Bart van Merriënboer , Thomas Unterthiner , Max Vladymyrov , Fabian Pedregosa

Neural networks (NN)-based learning algorithms are strongly affected by the choices of initialization and data distribution. Different optimization strategies have been proposed for improving the learning trajectory and finding a better…

Machine Learning · Computer Science 2021-03-19 Yimeng Min

We propose a reduced-space formulation for optimizing over trained neural networks where the network's outputs and derivatives are evaluated on a GPU. To do this, we treat the neural network as a "gray box" where intermediate variables and…

Machine Learning · Computer Science 2025-12-10 Robert Parker , Oscar Dowson , Nicole LoGiudice , Manuel Garcia , Russell Bent

Distributed optimization is the standard way of speeding up machine learning training, and most of the research in the area focuses on distributed first-order, gradient-based methods. Yet, there are settings where some…

Machine Learning · Computer Science 2025-11-03 Matin Ansaripour , Shayan Talaei , Giorgi Nadiradze , Dan Alistarh