中文
相关论文

相关论文: Smooth Optimization with Approximate Gradient

200 篇论文

This paper proposes a distributed algorithm for a network of agents to solve an optimization problem with separable objective function and locally coupled constraints. Our strategy is based on reformulating the original constrained problem…

最优化与控制 · 数学 2021-03-12 Priyank Srivastava , Jorge Cortes

A class of second-order algorithms is proposed for minimizing smooth nonconvex functions that alternates between regularized Newton and negative curvature steps in an iteration-dependent subspace. In most cases, the Hessian matrix is…

最优化与控制 · 数学 2023-08-22 Serge Gratton , Sadok Jerad , Philippe L. Toint

This paper shows that the optimal subgradient algorithm, OSGA, proposed in \cite{NeuO} can be used for solving structured large-scale convex constrained optimization problems. Only first-order information is required, and the optimal…

最优化与控制 · 数学 2015-01-08 Masoud Ahookhosh , Arnold Neumaier

We design and analyze a novel accelerated gradient-based algorithm for a class of bilevel optimization problems. These problems have various applications arising from machine learning and image processing, where optimal solutions of the two…

最优化与控制 · 数学 2023-11-20 Sepideh Samadi , Daniel Burbano , Farzad Yousefian

Optimization algorithms for solving nonconvex inverse problem have attracted significant interests recently. However, existing methods require the nonconvex regularization to be smooth or simple to ensure convergence. In this paper, we…

计算机视觉与模式识别 · 计算机科学 2020-03-26 Qingchao Zhang , Xiaojing Ye , Hongcheng Liu , Yunmei Chen

We consider minimization of a smooth nonconvex objective function using an iterative algorithm based on Newton's method and the linear conjugate gradient algorithm, with explicit detection and use of negative curvature directions for the…

最优化与控制 · 数学 2018-11-14 Clément W. Royer , Michael O'Neill , Stephen J. Wright

A new approach to solving eigenvalue optimization problems for large structured matrices is proposed and studied. The class of optimization problems considered is related to computing structured pseudospectra and their extremal points, and…

数值分析 · 数学 2022-06-22 Nicola Guglielmi , Christian Lubich , Stefano Sicilia

In this paper, we try to uncover the second-order essence of several first-order optimization methods. For Nesterov Accelerated Gradient, we rigorously prove that the algorithm makes use of the difference between past and current gradients,…

机器学习 · 计算机科学 2019-12-23 Yuzheng Hu , Licong Lin , Shange Tang

In this paper, we study neural networks from the point of view of nonsmooth optimisation, namely, quasidifferential calculus. We restrict ourselves to the case of uniform approximation by a neural network without hidden layers, the…

最优化与控制 · 数学 2025-03-05 Vinesha Peiris , Nadezda Sukhorukova

A new decomposition optimization algorithm, called \textit{path-following gradient-based decomposition}, is proposed to solve separable convex optimization problems. Unlike path-following Newton methods considered in the literature, this…

最优化与控制 · 数学 2012-09-21 Quoc Tran Dinh , Ion Necoara , Moritz Diehl

Nesterov's accelerated gradient algorithm is derived from first principles. The first principles are founded on the recently-developed optimal control theory for optimization. This theory frames an optimization problem as an optimal control…

最优化与控制 · 数学 2023-09-12 I. M. Ross

We consider semidefinite programs (SDPs) of size n with equality constraints. In order to overcome scalability issues, Burer and Monteiro proposed a factorized approach based on optimizing over a matrix Y of size $n$ by $k$ such that $X =…

机器学习 · 统计学 2018-11-29 Thomas Pumir , Samy Jelassi , Nicolas Boumal

Optimization plays a key role in machine learning. Recently, stochastic second-order methods have attracted much attention due to their low computational cost in each iteration. However, these algorithms might perform poorly especially if…

机器学习 · 计算机科学 2017-10-25 Haishan Ye , Zhihua Zhang

The total complexity (measured as the total number of gradient computations) of a stochastic first-order optimization algorithm that finds a first-order stationary point of a finite-sum smooth nonconvex objective function $F(w)=\frac{1}{n}…

This monograph presents the main complexity theorems in convex optimization and their corresponding algorithms. Starting from the fundamental theory of black-box optimization, the material progresses towards recent advances in structural…

最优化与控制 · 数学 2015-11-17 Sébastien Bubeck

Arising in semi-parametric statistics, control applications, and as sub-problems in global optimization methods, certain optimization problems can have objective functions requiring numerical integration to evaluate, yet gradient function…

最优化与控制 · 数学 2025-03-06 Christian Varner , Vivak Patel

Incorporating second order curvature information in gradient based methods have shown to improve convergence drastically despite its computational intensity. In this paper, we propose a stochastic (online) quasi-Newton method with…

机器学习 · 计算机科学 2020-10-16 S. Indrapriyadarsini , Shahrzad Mahboubi , Hiroshi Ninomiya , Hideki Asai

We analyze convergence rates of stochastic optimization procedures for non-smooth convex optimization problems. By combining randomized smoothing techniques with accelerated gradient methods, we obtain convergence rates of stochastic…

最优化与控制 · 数学 2012-04-10 John C. Duchi , Peter L. Bartlett , Martin J. Wainwright

In this paper, we generalize the well-known Nesterov's accelerated gradient (AG) method, originally designed for convex smooth optimization, to solve nonconvex and possibly stochastic optimization problems. We demonstrate that by properly…

最优化与控制 · 数学 2013-10-15 Saeed Ghadimi , Guanghui Lan

Various optimal gradient-based algorithms have been developed for smooth nonconvex optimization. However, many nonconvex machine learning problems do not belong to the class of smooth functions and therefore the existing algorithms are…

最优化与控制 · 数学 2023-06-27 Ziyi Chen , Yi Zhou , Yingbin Liang , Zhaosong Lu