中文
相关论文

相关论文: Refining asymptotic complexity bounds for nonconve…

200 篇论文

We provide sharp worst-case evaluation complexity bounds for nonconvex minimization problems with general inexpensive constraints, i.e.\ problems where the cost of evaluating/enforcing of the (possibly nonconvex or even disconnected)…

最优化与控制 · 数学 2021-05-31 Coralia Cartis , Nick I. M. Gould , Philippe L. Toint

We present a stochastic optimization method that uses a fourth-order regularized model to find local minima of smooth and potentially non-convex objective functions with a finite-sum structure. This algorithm uses sub-sampled derivatives…

最优化与控制 · 数学 2023-07-18 Aurelien Lucchi , Jonas Kohler

In this thesis we develop a novel framework to study smooth and strongly convex optimization algorithms, both deterministic and stochastic. Focusing on quadratic functions we are able to examine optimization algorithms as a recursive…

最优化与控制 · 数学 2014-10-24 Yossi Arjevani

We design an algorithm which finds an $\epsilon$-approximate stationary point (with $\|\nabla F(x)\|\le \epsilon$) using $O(\epsilon^{-3})$ stochastic gradient and Hessian-vector products, matching guarantees that were previously available…

机器学习 · 计算机科学 2020-06-25 Yossi Arjevani , Yair Carmon , John C. Duchi , Dylan J. Foster , Ayush Sekhari , Karthik Sridharan

We propose novel optimal and parameter-free algorithms for computing an approximate solution with small (projected) gradient norm. Specifically, for computing an approximate solution such that the norm of its (projected) gradient does not…

最优化与控制 · 数学 2024-11-18 Guanghui Lan , Yuyuan Ouyang , Zhe Zhang

We study a class of non-convex and non-smooth problems with \textit{rank} regularization to promote sparsity in optimal solution. We propose to apply the proximal gradient descent method to solve the problem and accelerate the process with…

最优化与控制 · 数学 2023-07-28 Mengyuan Zhang , Kai Liu

In this paper we address the convergence of stochastic approximation when the functions to be minimized are not convex and nonsmooth. We show that the "mean-limit" approach to the convergence which leads, for smooth problems, to the ODE…

最优化与控制 · 数学 2018-05-08 Szymon Majewski , Błażej Miasojedow , Eric Moulines

A fully stochastic second-order adaptive-regularization method for unconstrained nonconvex optimization is presented which never computes the objective-function value, but yet achieves the optimal $\mathcal{O}(\epsilon^{-3/2})$ complexity…

最优化与控制 · 数学 2025-01-22 Serge Gratton , Sadok Jerad , Philippe L. Toint

In this paper, an inexact proximal-point penalty method is studied for constrained optimization problems, where the objective function is non-convex, and the constraint functions can also be non-convex. The proposed method approximately…

最优化与控制 · 数学 2020-12-02 Qihang Lin , Runchao Ma , Yangyang Xu

It is well-known that the lower bound of iteration complexity for solving nonconvex unconstrained optimization problems is $\Omega(1/\epsilon^2)$, which can be achieved by standard gradient descent algorithm when the objective function is…

最优化与控制 · 数学 2022-11-02 Jiawei Zhang , Wenqiang Pu , Zhi-Quan Luo

We develop a worst-case evaluation complexity bound for trust-region methods in the presence of unbounded Hessian approximations. We use the algorithm of arXiv:2103.15993v3 as a model, which is designed for nonsmooth regularized problems,…

最优化与控制 · 数学 2025-10-14 Geoffroy Leconte , Dominique Orban

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

We present a new algorithm for solving optimization problems with objective functions that are the sum of a smooth function and a (potentially) nonsmooth regularization function, and nonlinear equality constraints. The algorithm may be…

最优化与控制 · 数学 2024-04-12 Yutong Dai , Xiaoyi Qu , Daniel P. Robinson

The problem of finding an optimum using noisy evaluations of a smooth cost function arises in many contexts, including economics, business, medicine, experiment design, and foraging theory. We derive an asymptotic bound E[ (x_t - x*)^2 ] >=…

机器学习 · 计算机科学 2007-05-23 Barak A. Pearlmutter

An algorithm for unconstrained non-convex optimization is described, which does not evaluate the objective function and in which minimization is carried out, at each iteration, within a randomly selected subspace. It is shown that this…

最优化与控制 · 数学 2025-01-31 S. Bellavia , S. Gratton , B. Morini , Ph. L. Toint

We develop a novel framework to study smooth and strongly convex optimization algorithms, both deterministic and stochastic. Focusing on quadratic functions we are able to examine optimization algorithms as a recursive application of linear…

最优化与控制 · 数学 2015-03-25 Yossi Arjevani , Shai Shalev-Shwartz , Ohad Shamir

This paper studies the complexity of projected gradient descent methods for a class of strongly convex constrained optimization problems where the objective function is expressed as a summation of $m$ component functions, each possessing a…

最优化与控制 · 数学 2026-02-10 Xiaojun Chen , C. T. Kelley , Lei Wang

Popular machine learning estimators involve regularization parameters that can be challenging to tune, and standard strategies rely on grid search for this task. In this paper, we revisit the techniques of approximating the regularization…

机器学习 · 统计学 2019-05-28 Eugene Ndiaye , Tam Le , Olivier Fercoq , Joseph Salmon , Ichiro Takeuchi

In this paper, we consider an unconstrained optimization model where the objective is a sum of a large number of possibly nonconvex functions, though overall the objective is assumed to be smooth and convex. Our bid to solving such model…

最优化与控制 · 数学 2022-03-15 Xi Chen , Bo Jiang , Tianyi Lin , Shuzhong Zhang

We establish or refute the optimality of inexact second-order methods for unconstrained nonconvex optimization from the point of view of worst-case evaluation complexity, improving and generalizing the results of Cartis, Gould and Toint…

最优化与控制 · 数学 2021-05-31 Coralia Cartis , Nick I. M. Gould , Philippe L. Toint