English
Related papers

Related papers: SGD_Tucker: A Novel Stochastic Optimization Strate…

200 papers

The tensor-train (TT) decomposition expresses a tensor in a data-sparse format used in molecular simulations, high-order correlation functions, and optimization. In this paper, we propose four parallelizable algorithms that compute the TT…

Numerical Analysis · Mathematics 2021-11-23 Tianyi Shi , Maximilian Ruth , Alex Townsend

In distributed machine learning, a central node outsources computationally expensive calculations to external worker nodes. The properties of optimization procedures like stochastic gradient descent (SGD) can be leveraged to mitigate the…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-04-19 Maximilian Egger , Serge Kas Hanna , Rawad Bitar

Stochastic nested optimization, including stochastic compositional, min-max and bilevel optimization, is gaining popularity in many machine learning applications. While the three problems share the nested structure, existing works often…

Machine Learning · Statistics 2021-06-28 Tianyi Chen , Yuejiao Sun , Wotao Yin

The Tucker decomposition expresses a given tensor as the product of a small core tensor and a set of factor matrices. Apart from providing data compression, the construction is useful in performing analysis such as principal component…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-07-19 Venkatesan T Chakaravarthy , Jee W Choi , Douglas J Joseph , Xing Liu , Prakash Murali , Yogish Sabharwal , Dheeraj Sreedhar

Stochastic Gradient Descent (SGD) is one of the simplest and most popular stochastic optimization methods. While it has already been theoretically studied for decades, the classical analysis usually required non-trivial smoothness…

Machine Learning · Computer Science 2013-01-01 Ohad Shamir , Tong Zhang

We provide improved parallel approximation algorithms for the important class of packing and covering linear programs. In particular, we present new parallel $\epsilon$-approximate packing and covering solvers which run in…

Data Structures and Algorithms · Computer Science 2015-11-23 Di Wang , Michael Mahoney , Nishanth Mohan , Satish Rao

Stochastic gradient descent (SGD) is a well known method for regression and classification tasks. However, it is an inherently sequential algorithm at each step, the processing of the current example depends on the parameters learned from…

Machine Learning · Computer Science 2017-05-24 Saeed Maleki , Madanlal Musuvathi , Todd Mytkowicz

Many relevant problems in the area of systems and control, such as controller synthesis, observer design and model reduction, can be viewed as optimization problems involving dynamical systems: for instance, maximizing performance in the…

Optimization and Control · Mathematics 2023-11-15 Pascal Den Boef , Jos Maubach , Wil Schilders , Nathan van de Wouw

The training of modern deep learning neural network calls for large amounts of computation, which is often provided by GPUs or other specific accelerators. To scale out to achieve faster training speed, two update algorithms are mainly…

Machine Learning · Computer Science 2020-05-15 Yemao Xu , Dezun Dong , Weixia Xu , Xiangke Liao

Stochastic gradient descent (SGD) holds as a classical method to build large scale machine learning models over big data. A stochastic gradient is typically calculated from a limited number of samples (known as mini-batch), so it…

Machine Learning · Computer Science 2016-01-14 Yadong Mu , Wei Liu , Wei Fan

We study the best low-rank Tucker decomposition of symmetric tensors. The motivating application is decomposing higher-order multivariate moments. Moment tensors have special structure and are important to various data science problems. We…

Numerical Analysis · Mathematics 2023-06-13 Ruhui Jin , Joe Kileel , Tamara G. Kolda , Rachel Ward

In this article, we consider the sparse tensor singular value decomposition, which aims for dimension reduction on high-dimensional high-order data with certain sparsity structure. A method named Sparse Tensor Alternating Thresholding for…

Statistics Theory · Mathematics 2024-07-09 Anru Zhang , Rungang Han

This paper presents fault-tolerant asynchronous Stochastic Gradient Descent (SGD) algorithms. SGD is widely used for approximating the minimum of a cost function $Q$, as a core part of optimization and learning algorithms. Our algorithms…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-06-14 Hagit Attiya , Noa Schiller

Stochastic gradient descent (SGD) is a widely used algorithm in machine learning, particularly for neural network training. Recent studies on SGD for canonical quadratic optimization or linear regression show it attains well generalization…

Machine Learning · Computer Science 2024-09-17 Haihan Zhang , Yuanshi Liu , Qianwen Chen , Cong Fang

Existing methods of vector autoregressive model for multivariate time series analysis make use of low-rank matrix approximation or Tucker decomposition to reduce the dimension of the over-parameterization issue. In this paper, we propose a…

Statistics Theory · Mathematics 2026-01-05 Sijia Xia , Michael K. Ng , Xiongjun Zhang

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

Tokenizers are a key component of state-of-the-art generative image models, extracting the most important features from the signal while reducing data dimension and redundancy. Most current tokenizers are based on KL-regularized variational…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Théophane Vallaeys , Jakob Verbeek , Matthieu Cord

Asynchronous stochastic gradient methods are central to scalable distributed optimization, particularly when devices differ in computational capabilities. Such settings arise naturally in federated learning, where training takes place on…

Optimization and Control · Mathematics 2026-02-20 Artavazd Maranjyan , Peter Richtárik

In this work, we describe advanced numerical tools for working with multivariate functions and for the analysis of large data sets. These tools will drastically reduce the required computing time and the storage cost, and, therefore, will…

Numerical Analysis · Mathematics 2018-07-04 Alexander Litvinenko , David Keyes , Venera Khoromskaia , Boris N. Khoromskij , Hermann G. Matthies

Classical stochastic gradient methods are well suited for minimizing expected-value objective functions. However, they do not apply to the minimization of a nonlinear function involving expected values or a composition of two expected-value…

Machine Learning · Statistics 2014-11-17 Mengdi Wang , Ethan X. Fang , Han Liu