中文
相关论文

相关论文: On the Complexity of Finite-Sum Smooth Optimizatio…

200 篇论文

It is well-known that given a smooth, bounded-from-below, and possibly nonconvex function, standard gradient-based methods can find $\epsilon$-stationary points (with gradient norm less than $\epsilon$) in $\mathcal{O}(1/\epsilon^2)$…

最优化与控制 · 数学 2022-10-28 Guy Kornowski , Ohad Shamir

We study optimal distributed first-order optimization algorithms when the network (i.e., communication constraints between the agents) changes with time. This problem is motivated by scenarios where agents experience network malfunctions.…

最优化与控制 · 数学 2019-12-02 Alexander Rogozin , César A. Uribe , Alexander Gasnikov , Nikolay Malkovsky , Angelia Nedić

Classical global convergence results for first-order methods rely on uniform smoothness and the \L{}ojasiewicz inequality. Motivated by properties of objective functions that arise in machine learning, we propose a non-uniform refinement of…

机器学习 · 计算机科学 2022-06-03 Jincheng Mei , Yue Gao , Bo Dai , Csaba Szepesvari , Dale Schuurmans

In the first part of the paper we consider accelerated first order optimization method for convex functions with $L$-Lipschitz-continuous gradient, that is able to automatically adapts to problems which satisfies Polyak-{\L}ojasiewicz…

最优化与控制 · 数学 2020-06-17 Nazarii Tupitsa

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…

最优化与控制 · 数学 2020-08-19 Huan Li , Cong Fang , Wotao Yin , Zhouchen Lin

Recent applications that arise in machine learning have surged significant interest in solving min-max saddle point games. This problem has been extensively studied in the convex-concave regime for which a global equilibrium solution can be…

最优化与控制 · 数学 2019-11-01 Maher Nouiehed , Maziar Sanjabi , Tianjian Huang , Jason D. Lee , Meisam Razaviyayn

Motivated by the emergence of federated learning (FL), we design and analyze federated methods for addressing: (i) Nondifferentiable nonconvex optimization; (ii) Bilevel optimization; (iii) Minimax problems; and (iv) Two-stage stochastic…

最优化与控制 · 数学 2025-07-04 Yuyang Qiu , Uday V. Shanbhag , Farzad Yousefian

We develop a Levenberg-Marquardt method for minimizing the sum of a smooth nonlinear least-squar es term $f(x) = \tfrac{1}{2} \|F(x)\|_2^2$ and a nonsmooth term $h$. Both $f$ and $h$ may be nonconvex. Steps are computed by minimizing the…

最优化与控制 · 数学 2023-01-09 Aleksandr Y. Aravkin , Robert Baraldi , Dominique Orban

We introduce PF-AGD, the first parameter-free, deterministic, accelerated first-order method to achieve $O(\epsilon^{-5/3}\log(1/\epsilon))$ oracle complexity bound when minimizing sufficiently smooth, non-convex functions; this is the…

最优化与控制 · 数学 2026-05-05 Sichao Xiong , Sadok Jerad , Coralia Cartis

Most existing rate and complexity guarantees for stochastic gradient methods in $L$-smooth settings mandates that such sequences be non-adaptive, non-increasing, and upper bounded by $\tfrac{a}{L}$ for $a > 0$. This requires knowledge of…

最优化与控制 · 数学 2025-12-18 Qi Wang , Uday V. Shanbhag , Yue Xie

This paper considers the problem of solving a special quartic-quadratic optimization problem with a single sphere constraint, namely, finding a global and local minimizer of…

最优化与控制 · 数学 2019-08-05 Haixiang Zhang , Andre Milzarek , Zaiwen Wen , Wotao Yin

We study the query complexity of min-max optimization of a nonconvex-nonconcave function $f$ over $[0,1]^d \times [0,1]^d$. We show that, given oracle access to $f$ and to its gradient $\nabla f$, any algorithm that finds an…

数据结构与算法 · 计算机科学 2026-05-14 Martino Bernasconi , Matteo Castiglioni , Andrea Celli , Alexandros Hollender

We propose a derivative-free trust-region method based on finite-difference gradient approximations for smooth optimization problems with convex constraints. The proposed method does not require computing an approximate stationarity…

最优化与控制 · 数学 2025-10-21 Dânâ Davar , Geovani Nunes Grapiglia

This work considers minimizing a sum of convex functions, each with potentially different structure ranging from nonsmooth to smooth, Lipschitz to non-Lipschitz. Nesterov's universal fast gradient method provides an optimal black-box…

最优化与控制 · 数学 2023-06-14 Benjamin Grimmer

We consider the minimization of an $L_0$-Lipschitz continuous and expectation-valued function, denoted by $f$ and defined as $f(x)\triangleq \mathbb{E}[\tilde{f}(x,\omega)]$, over a Cartesian product of closed and convex sets with a view…

最优化与控制 · 数学 2021-07-16 Uday V. Shanbhag , Farzad Yousefian

We present in this paper novel accelerated fully first-order methods in \emph{Bilevel Optimization} (BLO). Firstly, for BLO under the assumption that the lower-level functions admit the typical strong convexity assumption, the…

最优化与控制 · 数学 2024-07-10 Chris Junchi Li

In this paper, we consider a class of structured nonsmooth fractional minimization, where the first part of the objective is the ratio of a nonnegative nonsmooth nonconvex function to a nonnegative nonsmooth convex function, while the…

最优化与控制 · 数学 2025-12-25 Junpeng Zhou , Na Zhang , Qia Li

We introduce new optimized first-order methods for smooth unconstrained convex minimization. Drori and Teboulle recently described a numerical method for computing the $N$-iteration optimal step coefficients in a class of first-order…

最优化与控制 · 数学 2019-06-14 Donghwan Kim , Jeffrey A. Fessler

We consider a standard distributed optimisation setting where $N$ machines, each holding a $d$-dimensional function $f_i$, aim to jointly minimise the sum of the functions $\sum_{i = 1}^N f_i (x)$. This problem arises naturally in…

机器学习 · 计算机科学 2021-12-08 Dan Alistarh , Janne H. Korhonen

It is well known that there have been many numerical algorithms for solving nonsmooth minimax problems, numerical algorithms for nonsmooth minimax problems with joint linear constraints are very rare. This paper aims to discuss optimality…

最优化与控制 · 数学 2022-04-21 Yu-Hong Dai , Jiani Wang , Liwei Zhang