English
Related papers

Related papers: Supervised Descent Method for Solving Nonlinear Le…

200 papers

Stochastic gradient descent (SGD) is widely used in deep learning due to its computational efficiency, but a complete understanding of why SGD performs so well remains a major challenge. It has been observed empirically that most…

Machine Learning · Statistics 2022-06-20 Carmina Fjellström , Kaj Nyström

Surveillance scenarios are prone to several problems since they usually involve low-resolution footage, and there is no control of how far the subjects may be from the camera in the first place. This situation is suitable for the…

Computer Vision and Pattern Recognition · Computer Science 2021-01-27 Angelo G. Menezes

Novel coordinate descent (CD) methods are proposed for minimizing nonconvex functions consisting of three terms: (i) a continuously differentiable term, (ii) a simple convex term, and (iii) a concave and continuous term. First, by extending…

Optimization and Control · Mathematics 2019-09-15 Qi Deng , Chenghao Lan

By the asymptotic oracle property, non-convex penalties represented by minimax concave penalty (MCP) and smoothly clipped absolute deviation (SCAD) have attracted much attentions in high-dimensional data analysis, and have been widely used…

Computation · Statistics 2021-11-24 Peili Li , Min Liu , Zhou Yu

We consider gradient descent like algorithms for Support Vector Machine (SVM) training when the data is in relational form. The gradient of the SVM objective can not be efficiently computed by known techniques as it suffers from the…

Data Structures and Algorithms · Computer Science 2020-05-13 Mahmoud Abo-Khamis , Sungjin Im , Benjamin Moseley , Kirk Pruhs , Alireza Samadian

Stochastic gradient descent (SGD) has been a go-to algorithm for nonconvex stochastic optimization problems arising in machine learning. Its theory however often requires a strong framework to guarantee convergence properties. We hereby…

Optimization and Control · Mathematics 2025-03-11 Azar Louzi

Stochastic gradient descent (SGD) on a low-rank factorization is commonly employed to speed up matrix problems including matrix completion, subspace tracking, and SDP relaxation. In this paper, we exhibit a step size scheme for SGD on a…

Machine Learning · Computer Science 2015-02-11 Christopher De Sa , Kunle Olukotun , Christopher Ré

This paper introduces a novel Homogeneous Second-order Descent Ascent (HSDA) algorithm for nonconvex-strongly concave minimax optimization problems. At each iteration, HSDA uniquely computes a search direction by solving a homogenized…

Optimization and Control · Mathematics 2026-02-17 Jia-Hao Chen , Zi Xu , Hui-Ling Zhang

Self-supervised real-world image denoising remains a fundamental challenge, arising from the antagonistic trade-off between decorrelating spatially structured noise and preserving high-frequency details. Existing blind-spot network (BSN)…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Yiwen Shan , Haiyu Zhao , Peng Hu , Xi Peng , Yuanbiao Gou

Image denoising is a classical problem in low level computer vision. Model-based optimization methods and deep learning approaches have been the two main strategies for solving the problem. Model-based optimization methods are flexible for…

Computer Vision and Pattern Recognition · Computer Science 2018-12-31 Chang Liu , Zhaowei Shang , Anyong Qin

In this paper we discuss an application of Stochastic Approximation to statistical estimation of high-dimensional sparse parameters. The proposed solution reduces to resolving a penalized stochastic optimization problem on each stage of a…

Machine Learning · Statistics 2022-10-25 Sasila Ilandarideva , Yannis Bekri , Anatoli Juditsky , Vianney Perchet

Minimax problems have recently attracted a lot of research interests. A few efforts have been made to solve decentralized nonconvex strongly-concave (NCSC) minimax-structured optimization; however, all of them focus on smooth problems with…

Optimization and Control · Mathematics 2023-04-06 Yangyang Xu

We study a fundamental class of regression models called the second order linear model (SLM). The SLM extends the linear model to high order functional space and has attracted considerable research interest recently. Yet how to efficiently…

Machine Learning · Statistics 2017-06-26 Ming Lin , Shuang Qiu , Bin Hong , Jieping Ye

This work analyzes the convergence of a class of smoothing-based gradient descent methods when applied to optimization problems. In particular, Gaussian smoothing is employed to define a nonlocal gradient that reduces high-frequency noise,…

Optimization and Control · Mathematics 2024-03-27 Andrew Starnes , Anton Dereventsov , Clayton Webster

We introduce a machine-learning framework to learn the hyperparameter sequence of first-order methods (e.g., the step sizes in gradient descent) to quickly solve parametric convex optimization problems. Our computational architecture…

Optimization and Control · Mathematics 2024-12-23 Rajiv Sambharya , Bartolomeo Stellato

Optimization over the Stiefel manifold is a fundamental computational problem in many scientific and engineering applications. Despite considerable research effort, high-dimensional optimization problems over the Stiefel manifold remain…

Optimization and Control · Mathematics 2025-05-16 Andy Yat-Ming Cheung , Jinxin Wang , Man-Chung Yue , Anthony Man-Cho So

This paper investigates the problems large-scale distributed composite convex optimization, with motivations from a broad range of applications, including multi-agent systems, federated learning, smart grids, wireless sensor networks,…

Optimization and Control · Mathematics 2025-12-16 Maoran Wang , Xingju Cai , Yongxin Chen

Due to limited size and imperfect of the optical components in a spectrometer, aberration has inevitably been brought into two-dimensional multi-fiber spectrum image in LAMOST, which leads to obvious spacial variation of the point spread…

Instrumentation and Methods for Astrophysics · Physics 2020-10-28 Jiali Xu , Qian Yin , Ping Guo , Xin Zheng

Most modern learning problems are highly overparameterized, meaning that there are many more parameters than the number of training data points, and as a result, the training loss may have infinitely many global minima (parameter vectors…

Machine Learning · Computer Science 2019-06-11 Navid Azizan , Sahin Lale , Babak Hassibi

We propose an efficient hybrid least squares/gradient descent method to accelerate DeepONet training. Since the output of DeepONet can be viewed as linear with respect to the last layer parameters of the branch network, these parameters can…

Machine Learning · Computer Science 2025-08-22 Jun Choi , Chang-Ock Lee , Minam Moon