English
Related papers

Related papers: Problem-dependent convergence bounds for randomize…

200 papers

In this paper, we study the communication and (sub)gradient computation costs in distributed optimization and give a sharp complexity analysis for the proposed distributed accelerated gradient methods. We present two algorithms based on the…

Optimization and Control · Mathematics 2020-08-19 Huan Li , Cong Fang , Wotao Yin , Zhouchen Lin

We analyze the convergence of gradient-based optimization algorithms that base their updates on delayed stochastic gradient information. The main application of our results is to the development of gradient-based distributed optimization…

Optimization and Control · Mathematics 2011-05-02 Alekh Agarwal , John C. Duchi

Due to the substantial computational cost, training state-of-the-art deep neural networks for large-scale datasets often requires distributed training using multiple computation workers. However, by nature, workers need to frequently…

Machine Learning · Computer Science 2018-02-21 Yusuke Tsuzuku , Hiroto Imachi , Takuya Akiba

We study a distributed consensus-based stochastic gradient descent (SGD) algorithm and show that the rate of convergence involves the spectral properties of two matrices: the standard spectral gap of a weight matrix from the network…

Optimization and Control · Mathematics 2016-09-02 Avleen S. Bijral , Anand D. Sarwate , Nathan Srebro

A method of simultaneously optimizing both the structure of neural networks and the connection weights in a single training loop can reduce the enormous computational cost of neural architecture search. We focus on the probabilistic…

Neural and Evolutionary Computing · Computer Science 2022-05-27 Shota Saito , Shinichi Shirakawa

Bilevel programming has recently received attention in the literature due to its wide range of applications, including reinforcement learning and hyper-parameter optimization. However, it is widely assumed that the underlying bilevel…

Machine Learning · Computer Science 2024-10-11 Parvin Nazari , Ahmad Mousavi , Davoud Ataee Tarzanagh , George Michailidis

We consider an optimization problem with strongly convex objective and linear inequalities constraints. To be able to deal with a large number of constraints we provide a penalty reformulation of the problem. As penalty functions we use a…

Optimization and Control · Mathematics 2020-04-29 Angelia Nedich , Tatiana Tatarenko

It is well known that it is challenging to train deep neural networks and recurrent neural networks for tasks that exhibit long term dependencies. The vanishing or exploding gradient problem is a well known issue associated with these…

Machine Learning · Computer Science 2017-10-13 Eugene Vorontsov , Chiheb Trabelsi , Samuel Kadoury , Chris Pal

For minimizing a strongly convex objective function subject to linear inequality constraints, we consider a penalty approach that allows one to utilize stochastic methods for problems with a large number of constraints and/or objective…

Optimization and Control · Mathematics 2022-02-16 Meng Li , Paul Grigas , Alper Atamturk

Synthesis of optimization algorithms typically follows a {\em design-then-analyze\/} approach, which can obscure fundamental performance limits and hinder the systematic development of algorithms that operate near these limits. Recently, a…

Optimization and Control · Mathematics 2025-09-26 Ibrahim K. Ozaslan , Wuwei Wu , Jie Chen , Tryphon T. Georgiou , Mihailo R. Jovanovic

Distributed model training suffers from communication bottlenecks due to frequent model updates transmitted across compute nodes. To alleviate these bottlenecks, practitioners use gradient compression techniques like sparsification,…

Machine Learning · Computer Science 2020-11-02 Saurabh Agarwal , Hongyi Wang , Kangwook Lee , Shivaram Venkataraman , Dimitris Papailiopoulos

Sparse Gaussian graphical models characterize sparse dependence relationships between random variables in a network. To estimate multiple related Gaussian graphical models on the same set of variables, we formulate a hierarchical model,…

Methodology · Statistics 2014-06-10 Yuancheng Zhu , Rina Foygel Barber

Communication overhead severely hinders the scalability of distributed machine learning systems. Recently, there has been a growing interest in using gradient compression to reduce the communication overhead of the distributed training.…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-05-19 Yuchen Zhong , Cong Xie , Shuai Zheng , Haibin Lin

The emergence of big data has caused a dramatic shift in the operating regime for optimization algorithms. The performance bottleneck, which used to be computations, is now often communications. Several gradient compression techniques have…

Signal Processing · Electrical Eng. & Systems 2020-06-19 Sarit Khirirat , Sindri Magnússon , Mikael Johansson

In this paper, we consider a class of nonconvex problems with linear constraints appearing frequently in the area of image processing. We solve this problem by the penalty method and propose the iteratively reweighted alternating…

Optimization and Control · Mathematics 2019-02-13 Tao Sun , Dongsheng Li , Hao Jiang , Zhe Quan

We consider minimization problems with structured objective function and smooth constraints, and present a flexible framework that combines the beneficial regularization effects of (exact) penalty and interior-point methods. In the fully…

Optimization and Control · Mathematics 2025-08-27 Alberto De Marchi , Andreas Themelis

The ever-increasing parameter counts of deep learning models necessitate effective compression techniques for deployment on resource-constrained devices. This paper explores the application of information geometry, the study of…

Machine Learning · Computer Science 2025-07-15 Zakhar Shumaylov , Vasileios Tsiaras , Yannis Stylianou

Communication overhead is the key challenge for distributed training. Gradient compression is a widely used approach to reduce communication traffic. When combining with parallel communication mechanism method like pipeline, gradient…

Machine Learning · Computer Science 2021-09-08 Enda Yu , Dezun Dong , Yemao Xu , Shuo Ouyang , Xiangke Liao

This paper considers optimization problems over networks where agents have individual objectives to meet, or individual parameter vectors to estimate, subject to subspace constraints that require the objectives across the network to lie in…

Multiagent Systems · Computer Science 2020-04-22 Roula Nassif , Stefan Vlaski , Ali H. Sayed

In high-dimensional and/or non-parametric regression problems, regularization (or penalization) is used to control model complexity and induce desired structure. Each penalty has a weight parameter that indicates how strongly the structure…

Machine Learning · Statistics 2017-03-30 Jean Feng , Noah Simon