English
Related papers

Related papers: AdaCubic: An Adaptive Cubic Regularization Optimiz…

200 papers

Learning to improve AUC performance is an important topic in machine learning. However, AUC maximization algorithms may decrease generalization performance due to the noisy data. Self-paced learning is an effective method for handling noisy…

Machine Learning · Computer Science 2022-07-11 Bin Gu , Chenkang Zhang , Huan Xiong , Heng Huang

We introduce AdaSub, a stochastic optimization algorithm that computes a search direction based on second-order information in a low-dimensional subspace that is defined adaptively based on available current and past information. Compared…

Optimization and Control · Mathematics 2023-11-08 João Victor Galvão da Mata , Martin S. Andersen

The cubic regularization method (CR) and its adaptive version (ARC) are popular Newton-type methods in solving unconstrained non-convex optimization problems, due to its global convergence to local minima under mild conditions. The main aim…

Optimization and Control · Mathematics 2022-10-13 Yihang Gao , Michael K. Ng

When quantizing neural networks, assigning each floating-point weight to its nearest fixed-point value is the predominant approach. We find that, perhaps surprisingly, this is not the best we can do. In this paper, we propose AdaRound, a…

Machine Learning · Computer Science 2020-07-01 Markus Nagel , Rana Ali Amjad , Mart van Baalen , Christos Louizos , Tijmen Blankevoort

An algorithm for solving smooth nonconvex optimization problems is proposed that, in the worst-case, takes $\mathcal{O}(\epsilon^{-3/2})$ iterations to drive the norm of the gradient of the objective function below a prescribed positive…

Optimization and Control · Mathematics 2018-03-16 Frank E. Curtis , Daniel P. Robinson , Mohammadreza Samadi

Momentum is a popular technique to accelerate the convergence in practical training, and its impact on convergence guarantee has been well-studied for first-order algorithms. However, such a successful acceleration technique has not yet…

Optimization and Control · Mathematics 2019-06-28 Zhe Wang , Yi Zhou , Yingbin Liang , Guanghui Lan

We propose a stochastic variance-reduced cubic regularized Newton algorithm to optimize the finite-sum problem over a Riemannian submanifold of the Euclidean space. The proposed algorithm requires a full gradient and Hessian update at the…

Optimization and Control · Mathematics 2022-12-14 Dewei Zhang , Sam Davanloo Tajbakhsh

We propose a distributed, cubic-regularized Newton method for large-scale convex optimization over networks. The proposed method requires only local computations and communications and is suitable for federated learning applications over…

Optimization and Control · Mathematics 2020-07-08 César A. Uribe , Ali Jadbabaie

Hyperbolic deep learning has become a growing research direction in computer vision due to the unique properties afforded by the alternate embedding space. The negative curvature and exponentially growing distance metric provide a natural…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Ahmad Bdeir , Johannes Burchert , Lars Schmidt-Thieme , Niels Landwehr

We consider variants of trust-region and cubic regularization methods for non-convex optimization, in which the Hessian matrix is approximated. Under mild conditions on the inexact Hessian, and using approximate solution of the…

Optimization and Control · Mathematics 2019-05-15 Peng Xu , Fred Roosta , Michael W. Mahoney

Sharpness aware minimization (SAM) optimizer has been extensively explored as it can generalize better for training deep neural networks via introducing extra perturbation steps to flatten the landscape of deep learning models. Integrating…

Machine Learning · Computer Science 2023-03-02 Hao Sun , Li Shen , Qihuang Zhong , Liang Ding , Shixiang Chen , Jingwei Sun , Jing Li , Guangzhong Sun , Dacheng Tao

We consider empirical risk minimization for large-scale datasets. We introduce Ada Newton as an adaptive algorithm that uses Newton's method with adaptive sample sizes. The main idea of Ada Newton is to increase the size of the training set…

Machine Learning · Computer Science 2016-05-26 Aryan Mokhtari , Alejandro Ribeiro

Trust region and cubic regularization methods have demonstrated good performance in small scale non-convex optimization, showing the ability to escape from saddle points. Each iteration of these methods involves computation of gradient,…

Optimization and Control · Mathematics 2018-09-27 Liu Liu , Xuanqing Liu , Cho-Jui Hsieh , Dacheng Tao

We study finite-sum non-convex optimization $\min_{x\in\mathbb{R}^d} F(x) \;=\; \frac{1}{n}\sum_{i=1}^n f_i(x)$ and analyze a variance-reduced cubic Newton method based on EMA-smoothed SARAH estimators for both gradient and Hessian…

Optimization and Control · Mathematics 2026-04-28 Dmitry Pasechnyuk-Vilensky , Dmitry Kamzolov , Martin Takáč

Regularization in the optimization of deep neural networks is often critical to avoid undesirable over-fitting leading to better generalization of model. One of the most popular regularization algorithms is to impose L-2 penalty on the…

Machine Learning · Computer Science 2019-08-09 Kensuke Nakamura , Byung-Woo Hong

Quantization is a widely used technique to compress and accelerate deep neural networks. However, conventional quantization methods use the same bit-width for all (or most of) the layers, which often suffer significant accuracy degradation…

Computer Vision and Pattern Recognition · Computer Science 2021-10-14 Weihan Chen , Peisong Wang , Jian Cheng

This paper deals with nonconvex stochastic optimization problems in deep learning and provides appropriate learning rates with which adaptive learning rate optimization algorithms, such as Adam and AMSGrad, can approximate a stationary…

Optimization and Control · Mathematics 2020-11-24 Hideaki Iiduka

In a previous publication we proposed discrete global optimization as a method to train a strong binary classifier constructed as a thresholded sum over weak classifiers. Our motivation was to cast the training of a classifier into a format…

Quantum Physics · Physics 2009-12-07 Hartmut Neven , Vasil S. Denchev , Geordie Rose , William G. Macready

Distributed optimization is widely used in large-scale and privacy-preserving machine learning, where each agent stores a local objective and communicates only with its neighbors in a connected network. We study decentralized second-order…

Newton's method is the most widespread high-order method, demanding the gradient and the Hessian of the objective function. However, one of the main disadvantages of Newtons method is its lack of global convergence and high iteration cost.…