English
Related papers

Related papers: Projected Gradient Descent for Spectral Compressed…

200 papers

Subspace minimization conjugate gradient (SMCG) methods have become a class of quite efficient iterative methods for unconstrained optimization and have attracted extensive attention recently. Usually, the search directions of SMCG methods…

Optimization and Control · Mathematics 2023-03-24 Zexian Liu , Yan Ni , Hongwei Liu , Wumei Sun

We propose a family of adaptive integer compression operators for distributed Stochastic Gradient Descent (SGD) that do not communicate a single float. This is achieved by multiplying floating-point vectors with a number known to every…

Machine Learning · Computer Science 2022-03-22 Konstantin Mishchenko , Bokun Wang , Dmitry Kovalev , Peter Richtárik

We present a computationally-efficient method for recovering sparse signals from a series of noisy observations, known as the problem of compressed sensing (CS). CS theory requires solving a convex constrained minimization problem. We…

Information Theory · Computer Science 2010-06-22 Avishy Carmi , Pini Gurfil

We propose LQ-SGD (Low-Rank Quantized Stochastic Gradient Descent), an efficient communication gradient compression algorithm designed for distributed training. LQ-SGD further develops on the basis of PowerSGD by incorporating the low-rank…

Machine Learning · Computer Science 2025-06-24 Hongyang Li , Lincen Bai , Caesar Wu , Mohammed Chadli , Said Mammar , Pascal Bouvry

Stochastic Gradient Descent (SGD) is a known stochastic iterative method popular for large-scale convex optimization problems due to its simple implementation and scalability. Some objectives, such as those found in complex-valued neural…

Machine Learning · Computer Science 2026-05-26 Natanael Alpay , Emeric Battaglia

In this paper we analyze the behaviour of the stochastic gradient descent (SGD), a widely used method in supervised learning for optimizing neural network weights via a minimization of non-convex loss functions. Since the pioneering work of…

Machine Learning · Computer Science 2025-05-13 Davide Barbieri , Matteo Bonforte , Peio Ibarrondo

Communication compression techniques are of growing interests for solving the decentralized optimization problem under limited communication, where the global objective is to minimize the average of local cost functions over a multi-agent…

Optimization and Control · Mathematics 2022-05-26 Yiwei Liao , Zhuorui Li , Kun Huang , Shi Pu

In this paper, we provide the first convergence guarantee for the factorization approach. Specifically, to avoid the scaling ambiguity and to facilitate theoretical analysis, we optimize over the so-called left-orthogonal TT format which…

Machine Learning · Statistics 2025-09-01 Zhen Qin , Michael B. Wakin , Zhihui Zhu

We analyze (stochastic) gradient descent (SGD) with delayed updates on smooth quasi-convex and non-convex functions and derive concise, non-asymptotic, convergence rates. We show that the rate of convergence in all cases consists of two…

Machine Learning · Computer Science 2021-06-17 Sebastian U. Stich , Sai Praneeth Karimireddy

In this paper, we propose a novel kernel stochastic gradient descent (SGD) algorithm for large-scale supervised learning with general losses. Compared to traditional kernel SGD, our algorithm improves efficiency and scalability through an…

Machine Learning · Computer Science 2026-04-28 Jinhui Bai , Andreas Christmann , Lei Shi

In practical instances of nonconvex matrix factorization, the rank of the true solution $r^{\star}$ is often unknown, so the rank $r$ of the model can be overspecified as $r>r^{\star}$. This over-parameterized regime of matrix factorization…

Optimization and Control · Mathematics 2025-04-15 Gavin Zhang , Salar Fattahi , Richard Y. Zhang

In this paper, we investigate a general class of stochastic gradient descent (SGD) algorithms, called Conditioned SGD, based on a preconditioning of the gradient direction. Using a discrete-time approach with martingale tools, we establish…

Statistics Theory · Mathematics 2023-10-17 Rémi Leluc , François Portier

This paper focuses on recovering a low-rank tensor from its incomplete measurements. We propose a novel algorithm termed the Single Mode Quasi Riemannian Gradient Descent (SM-QRGD). By exploiting the benefits of both fixed-rank matrix…

Optimization and Control · Mathematics 2024-01-30 Yuanwei Zhang , Ya-Nan Zhu , Xiaoqun Zhang

Low-rank gradient compression methods, such as PowerSGD, have gained attention in communication-efficient distributed optimization. However, the convergence guarantees of PowerSGD remain unclear, particularly in stochastic settings. In this…

Optimization and Control · Mathematics 2025-09-16 Shengping Xie , Chuyan Chen , Kun Yuan

This paper investigates the recovery of a spectrally sparse signal from its partially revealed noisy entries within the framework of spectral compressive sensing. Nonconvex optimization approaches have recently been proposed based on…

Information Theory · Computer Science 2022-01-25 Xunmeng Wu , Zai Yang , Zongben Xu

Tensors, which provide a powerful and flexible model for representing multi-attribute data and multi-way interactions, play an indispensable role in modern data science across various fields in science and engineering. A fundamental task is…

Machine Learning · Computer Science 2022-06-23 Tian Tong , Cong Ma , Ashley Prater-Bennette , Erin Tripp , Yuejie Chi

The problem of low-tubal-rank tensor estimation is a fundamental task with wide applications across high-dimensional signal processing, machine learning, and image science. Traditional approaches tackle such a problem by performing tensor…

Machine Learning · Computer Science 2025-12-24 Zhiyu Liu , Zhi Han , Yandong Tang , Jun Fan , Yao Wang

Gradient dominance property is a condition weaker than strong convexity, yet sufficiently ensures global convergence even in non-convex optimization. This property finds wide applications in machine learning, reinforcement learning (RL),…

Optimization and Control · Mathematics 2024-05-30 Jiyuan Tan , Chenyu Xue , Chuwen Zhang , Qi Deng , Dongdong Ge , Yinyu Ye

Tensor decompositions, which represent an $N$-order tensor using approximately $N$ factors of much smaller dimensions, can significantly reduce the number of parameters. This is particularly beneficial for high-order tensors, as the number…

Machine Learning · Computer Science 2025-06-23 Zhen Qin , Michael B. Wakin , Zhihui Zhu

For the problem of reconstructing a low-rank matrix from a few linear measurements, two classes of algorithms have been widely studied in the literature: convex approaches based on nuclear norm minimization, and non-convex approaches that…

Machine Learning · Statistics 2025-07-29 Dominik Stöger , Yizhe Zhu