English
Related papers

Related papers: AdaCubic: An Adaptive Cubic Regularization Optimiz…

200 papers

We propose and analyze random subspace variants of the second-order Adaptive Regularization using Cubics (ARC) algorithm. These methods iteratively restrict the search space to some random subspace of the parameters, constructing and…

Optimization and Control · Mathematics 2025-01-17 Coralia Cartis , Zhen Shao , Edward Tansley

We propose a randomized algorithm with quadratic convergence rate for convex optimization problems with a self-concordant, composite, strongly convex objective function. Our method is based on performing an approximate Newton step using a…

Optimization and Control · Mathematics 2021-05-18 Jonathan Lacotte , Yifei Wang , Mert Pilanci

Deep neural networks are traditionally trained using human-designed stochastic optimization algorithms, such as SGD and Adam. Recently, the approach of learning to optimize network parameters has emerged as a promising research topic.…

Machine Learning · Computer Science 2018-11-26 Shipeng Wang , Jian Sun , Zongben Xu

The adaptive gradient online learning method known as AdaGrad has seen widespread use in the machine learning community in stochastic and adversarial online learning problems and more recently in deep learning methods. The method's…

Machine Learning · Computer Science 2016-10-05 Nishant A. Mehta , Alistair Rendell , Anish Varghese , Christfried Webers

Real-world large-scale datasets are heteroskedastic and imbalanced -- labels have varying levels of uncertainty and label distributions are long-tailed. Heteroskedasticity and imbalance challenge deep learning algorithms due to the…

Machine Learning · Computer Science 2021-03-19 Kaidi Cao , Yining Chen , Junwei Lu , Nikos Arechiga , Adrien Gaidon , Tengyu Ma

This paper describes how to make the problem of binary classification amenable to quantum computing. A formulation is employed in which the binary classifier is constructed as a thresholded linear superposition of a set of weak classifiers.…

Quantum Physics · Physics 2008-11-05 Hartmut Neven , Vasil S. Denchev , Geordie Rose , William G. Macready

The cubic regularization method (CR) is a popular algorithm for unconstrained non-convex optimization. At each iteration, CR solves a cubically regularized quadratic problem, called the cubic regularization subproblem (CRS). One way to…

Optimization and Control · Mathematics 2022-09-28 Yihang Gao , Man-Chung Yue , Michael K. Ng

Deep neural networks with adaptive configurations have gained increasing attention due to the instant and flexible deployment of these models on platforms with different resource budgets. In this paper, we investigate a novel option to…

Computer Vision and Pattern Recognition · Computer Science 2020-03-17 Qing Jin , Linjie Yang , Zhenyu Liao

With the widespread applications of neural networks (NNs) trained on personal data, machine unlearning has become increasingly important for enabling individuals to exercise their personal data ownership, particularly the "right to be…

Machine Learning · Computer Science 2024-08-28 Nhung Bui , Xinyang Lu , Rachael Hwee Ling Sim , See-Kiong Ng , Bryan Kian Hsiang Low

For solving large-scale non-convex problems, we propose inexact variants of trust region and adaptive cubic regularization methods, which, to increase efficiency, incorporate various approximations. In particular, in addition to approximate…

Optimization and Control · Mathematics 2018-02-21 Zhewei Yao , Peng Xu , Farbod Roosta-Khorasani , Michael W. Mahoney

Optimization in Deep Learning is mainly dominated by first-order methods which are built around the central concept of backpropagation. Second-order optimization methods, which take into account the second-order derivatives are far less…

Machine Learning · Computer Science 2021-04-09 Fares B. Mehouachi , Chaouki Kasmi

Class-Incremental Learning aims to update a deep classifier to learn new categories while maintaining or improving its accuracy on previously observed classes. Common methods to prevent forgetting previously learned classes include…

Machine Learning · Computer Science 2024-07-02 Elif Ceren Gok Yildirim , Murat Onur Yildirim , Mert Kilickaya , Joaquin Vanschoren

Gradient descent-ascent (GDA) is a widely used algorithm for minimax optimization. However, GDA has been proved to converge to stationary points for nonconvex minimax optimization, which are suboptimal compared with local minimax points. In…

Optimization and Control · Mathematics 2023-02-21 Ziyi Chen , Zhengyang Hu , Qunwei Li , Zhe Wang , Yi Zhou

Optimization is essential in deep learning. The foundational method upon which most optimizers are built is momentum-based stochastic gradient descent. However, it suffers from two key drawbacks. First, it has noisy and varying gradients,…

Machine Learning · Computer Science 2026-05-22 Saurabh Saini , Kapil Ahuja , Thomas Wick , Saurav Kumar

We propose a continuous-time scheme for large-scale optimization that introduces individual, adaptive momentum coefficients regulated by the kinetic energy of each model parameter. This approach automatically adjusts to local landscape…

Machine Learning · Computer Science 2026-02-03 Aikaterini Karoni , Rajit Rajpal , Benedict Leimkuhler , Gabriel Stoltz

Despite the recent success of deep learning models in numerous applications, their widespread use on mobile devices is seriously impeded by storage and computational requirements. In this paper, we propose a novel network compression method…

Computer Vision and Pattern Recognition · Computer Science 2019-06-19 Zhisheng Zhong , Fangyin Wei , Zhouchen Lin , Chao Zhang

High-order tensor methods for solving both convex and nonconvex optimization problems have generated significant research interest, leading to algorithms with optimal global rates of convergence and local rates that are faster than Newton's…

Optimization and Control · Mathematics 2023-12-25 Wenqi Zhu , Coralia Cartis

Robustness and compactness are two essential attributes of deep learning models that are deployed in the real world. The goals of robustness and compactness may seem to be at odds, since robustness requires generalization across domains,…

Machine Learning · Computer Science 2024-03-14 Anna Bair , Hongxu Yin , Maying Shen , Pavlo Molchanov , Jose Alvarez

We design a new adaptive learning algorithm for misclassification cost problems that attempt to reduce the cost of misclassified instances derived from the consequences of various errors. Our algorithm (adaptive cost sensitive learning -…

Machine Learning · Computer Science 2021-11-16 Ohad Volk , Gonen Singer

We consider solving equality-constrained nonlinear, nonconvex optimization problems. This class of problems appears widely in a variety of applications in machine learning and engineering, ranging from constrained deep neural networks, to…

Optimization and Control · Mathematics 2023-05-31 Ilgee Hong , Sen Na , Michael W. Mahoney , Mladen Kolar