English
Related papers

Related papers: Accelerated Minimax Algorithms Flock Together

200 papers

This paper extends the algorithm schemes proposed in \cite{Nesterov2007a} and \cite{Nesterov2007b} to the minimization of the sum of a composite objective function and a convex function. Two proximal point-type schemes are provided and…

Optimization and Control · Mathematics 2011-05-03 Quoc Tran Dinh , Moritz Diehl

We show that stochastic acceleration can be achieved under the perturbed iterate framework (Mania et al., 2017) in asynchronous lock-free optimization, which leads to the optimal incremental gradient complexity for finite-sum objectives. We…

Optimization and Control · Mathematics 2021-10-01 Kaiwen Zhou , Anthony Man-Cho So , James Cheng

First-order methods play a central role in large-scale machine learning. Even though many variations exist, each suited to a particular problem, almost all such methods fundamentally rely on two types of algorithmic steps: gradient descent,…

Data Structures and Algorithms · Computer Science 2016-11-08 Zeyuan Allen-Zhu , Lorenzo Orecchia

Analysis of the convergence rates of modern convex optimization algorithms can be achived through binary means: analysis of emperical convergence, or analysis of theoretical convergence. These two pathways of capturing information diverge…

Machine Learning · Computer Science 2013-05-20 Patrick Hop , Xinghao Pan

Since Nesterov's seminal 1983 work, many accelerated first-order optimization methods have been proposed, but their analyses lacks a common unifying structure. In this work, we identify a geometric structure satisfied by a wide range of…

Optimization and Control · Mathematics 2021-11-05 Jongmin Lee , Chanwoo Park , Ernest K. Ryu

Existing asynchronous distributed optimization algorithms often use diminishing step-sizes that cause slow practical convergence, or use fixed step-sizes that depend on and decrease with an upper bound of the delays. Not only are such delay…

Optimization and Control · Mathematics 2024-11-08 Xuyang Wu , Changxin Liu , Sindri Magnusson , Mikael Johansson

Quasar convexity is a condition that allows some first-order methods to efficiently minimize a function even when the optimization landscape is non-convex. Previous works develop near-optimal accelerated algorithms for minimizing this class…

Optimization and Control · Mathematics 2023-02-16 Jun-Kun Wang , Andre Wibisono

In this paper, we consider nonconvex minimax optimization, which is gaining prominence in many modern machine learning applications such as GANs. Large-scale edge-based collection of training data in these applications calls for…

Optimization and Control · Mathematics 2022-03-10 Pranay Sharma , Rohan Panda , Gauri Joshi , Pramod K. Varshney

In this paper we propose a fast optimization algorithm for approximately minimizing convex quadratic functions over the intersection of affine and separable constraints (i.e., the Cartesian product of possibly nonconvex real sets). This…

Optimization and Control · Mathematics 2015-09-29 Reza Takapoui , Nicholas Moehle , Stephen Boyd , Alberto Bemporad

In this work we propose a differential geometric motivation for Nesterov's accelerated gradient method (AGM) for strongly-convex problems. By considering the optimization procedure as occurring on a Riemannian manifold with a natural…

Machine Learning · Computer Science 2019-11-21 Aaron Defazio

Distributed algorithms for solving additive or consensus optimization problems commonly rely on first-order or proximal splitting methods. These algorithms generally come with restrictive assumptions and at best enjoy a linear convergence…

Optimization and Control · Mathematics 2017-05-11 Sina Khoshfetrat Pakazad , Christian A. Naesseth , Fredrik Lindsten , Anders Hansson

The present research work proposes a new fast fixed-point averaging algorithm on the compact Stiefel manifold based on a mixed retraction/lifting pair. Numerical comparisons between fixed-point algorithms based on the proposed…

Numerical Analysis · Mathematics 2013-03-08 Simone Fiori , Tetsuya Kaneko , Toshihisa Tanaka

This note provides a novel, simple analysis of the method of conjugate gradients for the minimization of convex quadratic functions. In contrast with standard arguments, our proof is entirely self-contained and does not rely on the…

Optimization and Control · Mathematics 2020-02-11 Jelena Diakonikolas , Lorenzo Orecchia

We propose a hybrid control algorithm that guarantees fast convergence and uniform global asymptotic stability of the unique minimizer of a continuously differentiable, convex objective function. The algorithm, developed using hybrid system…

Optimization and Control · Mathematics 2023-10-10 Dawn M. Hustig-Schultz , Ricardo G. Sanfelice

Nesterov's accelerated gradient methods (AGM) have been successfully applied in many machine learning areas. However, their empirical performance on training max-margin models has been inferior to existing specialized solvers. In this…

Machine Learning · Computer Science 2010-11-03 Xinhua Zhang , Ankan Saha , S. V. N. Vishwanathan

Recently, {\it stochastic momentum} methods have been widely adopted in training deep neural networks. However, their convergence analysis is still underexplored at the moment, in particular for non-convex optimization. This paper fills the…

Optimization and Control · Mathematics 2016-05-06 Tianbao Yang , Qihang Lin , Zhe Li

We provide new adaptive first-order methods for constrained convex optimization. Our main algorithms AdaACSA and AdaAGD+ are accelerated methods, which are universal in the sense that they achieve nearly-optimal convergence rates for both…

Machine Learning · Computer Science 2021-02-17 Alina Ene , Huy L. Nguyen , Adrian Vladu

We study Nesterov's accelerated gradient method with constant step-size and momentum parameters in the stochastic approximation setting (unbiased gradients with bounded variance) and the finite-sum setting (where randomness is due to…

Machine Learning · Computer Science 2020-06-30 Mahmoud Assran , Michael Rabbat

State-of-the-art algorithms for sparse subspace clustering perform spectral clustering on a similarity matrix typically obtained by representing each data point as a sparse combination of other points using either basis pursuit (BP) or…

Machine Learning · Computer Science 2017-11-02 Abolfazl Hashemi , Haris Vikalo

In recent years, even though Stochastic Gradient Descent (SGD) and its variants are well-known for training neural networks, it suffers from limitations such as the lack of theoretical guarantees, vanishing gradients, and excessive…

Optimization and Control · Mathematics 2022-02-17 Junxiang Wang , Hongyi Li , Liang Zhao