English
Related papers

Related papers: Semismooth Newton Coordinate Descent Algorithm for…

200 papers

Analog crossbar arrays comprising programmable nonvolatile resistors are under intense investigation for acceleration of deep neural network training. However, the ubiquitous asymmetric conductance modulation of practical resistive devices…

Block-coordinate descent (BCD) is the method of choice to solve numerous large scale optimization problems, however their theoretical study for non-convex optimization, has received less attention. In this paper, we present a new…

Machine Learning · Computer Science 2026-01-30 Guillaume Lauga

The training of deep neural networks is inherently a nonconvex optimization problem, yet standard approaches such as stochastic gradient descent (SGD) require simultaneous updates to all parameters, often leading to unstable convergence and…

Machine Learning · Computer Science 2025-08-07 Chengcheng Yan , Jiawei Xu , Zheng Peng , Qingsong Wang

A least-squares neural network (LSNN) method was introduced for solving scalar linear and nonlinear hyperbolic conservation laws (HCLs) in [7, 6]. This method is based on an equivalent least-squares (LS) formulation and uses ReLU neural…

Numerical Analysis · Mathematics 2023-05-09 Zhiqiang Cai , Jingshuang Chen , Min Liu

Under mild conditions on the noise level of the measurements, rotation averaging satisfies strong duality, which enables global solutions to be obtained via semidefinite programming (SDP) relaxation. However, generic solvers for SDP are…

Computer Vision and Pattern Recognition · Computer Science 2021-03-17 Álvaro Parra , Shin-Fang Chng , Tat-Jun Chin , Anders Eriksson , Ian Reid

Modern supervised learning techniques, particularly those using deep nets, involve fitting high dimensional labelled data sets with functions containing very large numbers of parameters. Much of this work is empirical. Interesting phenomena…

Machine Learning · Statistics 2018-05-30 Partha P Mitra

In this paper, we propose a learned scalable/progressive image compression scheme based on deep neural networks (DNN), named Bidirectional Context Disentanglement Network (BCD-Net). For learning hierarchical representations, we first adopt…

Multimedia · Computer Science 2019-04-23 Zhizheng Zhang , Zhibo Chen , Jianxin Lin , Weiping Li

Theoretically understanding stochastic gradient descent (SGD) in overparameterized models has led to the development of several optimization algorithms that are widely used in practice today. Recent work by~\citet{zou2021benign} provides…

Machine Learning · Computer Science 2025-06-19 Alexandru Meterez , Depen Morwani , Costin-Andrei Oncescu , Jingfeng Wu , Cengiz Pehlevan , Sham Kakade

In this paper, we propose a method of distributed stochastic gradient descent (SGD), with low communication load and computational complexity, and still fast convergence. To reduce the communication load, at each iteration of the algorithm,…

Machine Learning · Computer Science 2020-03-30 Naeimeh Omidvar , Mohammad Ali Maddah-Ali , Hamed Mahdavi

In this paper, we consider high-dimensional nonconvex square-root-loss regression problems and introduce a proximal majorization-minimization (PMM) algorithm for these problems. Our key idea for making the proposed PMM to be efficient is to…

Optimization and Control · Mathematics 2020-05-28 Peipei Tang , Chengjing Wang , Defeng Sun , Kim-Chuan Toh

We study the stochastic linear bandits with heavy-tailed noise. Two principled strategies for handling heavy-tailed noise, truncation and median-of-means, have been introduced to heavy-tailed bandits. Nonetheless, these methods rely on…

Machine Learning · Computer Science 2025-06-13 Jing Wang , Yu-Jie Zhang , Peng Zhao , Zhi-Hua Zhou

This paper studies the performance of a recently proposed preconditioned stochastic gradient descent (PSGD) algorithm on recurrent neural network (RNN) training. PSGD adaptively estimates a preconditioner to accelerate gradient descent, and…

Machine Learning · Statistics 2016-12-09 Xi-Lin Li

This paper develops asymptotic theory for quantile estimation via stochastic gradient descent (SGD) with a constant learning rate. The quantile loss function is neither smooth nor strongly convex. Beyond conventional perspectives and…

Machine Learning · Statistics 2026-04-06 Ziyang Wei , Jiaqi Li , Likai Chen , Wei Biao Wu

Single Image Super-Resolution (SISR) is one of the low-level computer vision problems that has received increased attention in the last few years. Current approaches are primarily based on harnessing the power of deep learning models and…

Computer Vision and Pattern Recognition · Computer Science 2021-05-19 Santiago López-Tapia , Nicolás Pérez de la Blanca

Training a neural network (NN) typically relies on some type of curve-following method, such as gradient descent (GD) (and stochastic gradient descent (SGD)), ADADELTA, ADAM or limited memory algorithms. Convergence for these algorithms…

Machine Learning · Computer Science 2023-05-08 Michael A Kouritzin , Stephen Styles , Beatrice-Helen Vritsiou

In this paper, we use Proximal Cubic regularized Newton Methods (PCNM) to optimize the sum of a smooth convex function and a non-smooth convex function, where we use inexact gradient and Hessian, and an inexact subsolver for the cubic…

Optimization and Control · Mathematics 2019-02-27 Chaobing Song , Ji Liu , Yong Jiang

In this paper, we focus on distributed estimation and support recovery for high-dimensional linear quantile regression. Quantile regression is a popular alternative tool to the least squares regression for robustness against outliers and…

Machine Learning · Statistics 2024-06-04 Caixing Wang , Ziliang Shen

We develop a fast and robust algorithm for solving large scale convex composite optimization models with an emphasis on the $\ell_1$-regularized least squares regression (Lasso) problems. Despite the fact that there exist a large number of…

Optimization and Control · Mathematics 2017-05-04 Xudong Li , Defeng Sun , Kim-Chuan Toh

We propose an efficient distributed randomized coordinate descent method for minimizing regularized non-strongly convex loss functions. The method attains the optimal $O(1/k^2)$ convergence rate, where $k$ is the iteration counter. The core…

Optimization and Control · Mathematics 2014-07-29 Olivier Fercoq , Zheng Qu , Peter Richtárik , Martin Takáč

In this paper, we introduce a novel and robust approach to Quantized Matrix Completion (QMC). First, we propose a rank minimization problem with constraints induced by quantization bounds. Next, we form an unconstrained optimization problem…

Machine Learning · Statistics 2019-02-20 Ashkan Esmaeili , Farokh Marvasti