中文
相关论文

相关论文: Glocal Smoothness: Line search and adaptive step s…

200 篇论文

The choice of the stepsize in first-order convex optimization is typically based on the smoothness constant and plays a crucial role in the performance of algorithms. Recently, there has been a resurgent interest in introducing adaptive…

最优化与控制 · 数学 2025-12-04 Reza Rahimi Baghbadorani , Sergio Grammatico , Peyman Mohajerin Esfahani

We study gradient methods for optimizing $(L_0, L_1)$-smooth functions, a class that generalizes Lipschitz-smooth functions and has gained attention for its relevance in machine learning. We provide new insights into the structure of this…

最优化与控制 · 数学 2025-03-11 Daniil Vankov , Anton Rodomanov , Angelia Nedich , Lalitha Sankar , Sebastian U. Stich

We introduce in this paper an optimal first-order method that allows an easy and cheap evaluation of the local Lipschitz constant of the objective's gradient. This constant must ideally be chosen at every iteration as small as possible,…

最优化与控制 · 数学 2012-07-18 Michel Baes , Michael Buergisser

Randomized smoothing is a widely adopted technique for optimizing nonsmooth objective functions. However, its efficiency analysis typically relies on global Lipschitz continuity, a condition rarely met in practical applications. To address…

最优化与控制 · 数学 2025-09-10 Jingfan Xia , Zhenwei Lin , Qi Deng

This paper discusses several (sub)gradient methods attaining the optimal complexity for smooth problems with Lipschitz continuous gradients, nonsmooth problems with bounded variation of subgradients, weakly smooth problems with H\"older…

最优化与控制 · 数学 2016-05-02 Masoud Ahookhosh

Regularization is a widely recognized technique in mathematical optimization. It can be used to smooth out objective functions, refine the feasible solution set, or prevent overfitting in machine learning models. Due to its simplicity and…

This paper deals with two kinds of the one-dimensional global optimization problems over a closed finite interval: (i) the objective function $f(x)$ satisfies the Lipschitz condition with a constant $L$; (ii) the first derivative of $f(x)$…

最优化与控制 · 数学 2013-07-15 Daniela Lera , Yaroslav D. Sergeyev

There has been much recent interest in finding unconstrained local minima of smooth functions, due in part of the prevalence of such problems in machine learning and robust statistics. A particular focus is algorithms with good complexity…

最优化与控制 · 数学 2017-12-12 Clément W. Royer , Stephen J. Wright

We study the optimization of non-convex functions that are not necessarily smooth (gradient and/or Hessian are Lipschitz) using first order methods. Smoothness is a restrictive assumption in machine learning in both theory and practice,…

最优化与控制 · 数学 2025-06-27 Daniel Yiming Cao , August Y. Chen , Karthik Sridharan , Benjamin Tang

First-order algorithms have been popular for solving convex and non-convex optimization problems. A key assumption for the majority of these algorithms is that the gradient of the objective function is globally Lipschitz continuous, but…

最优化与控制 · 数学 2024-02-07 Junyu Zhang , Mingyi Hong

We initiate a program of average smoothness analysis for efficiently learning real-valued functions on metric spaces. Rather than using the Lipschitz constant as the regularizer, we define a local slope at each point and gauge the function…

统计理论 · 数学 2020-11-10 Yair Ashlagi , Lee-Ad Gottlieb , Aryeh Kontorovich

Due to the non-smoothness of optimization problems in Machine Learning, generalized smoothness assumptions have been gaining a lot of attention in recent years. One of the most popular assumptions of this type is $(L_0,L_1)$-smoothness…

In machine learning applications, it is well known that carefully designed learning rate (step size) schedules can significantly improve the convergence of commonly used first-order optimization algorithms. Therefore how to set step size…

最优化与控制 · 数学 2023-10-19 Xiaoyu Wang , Mikael Johansson , Tong Zhang

The analysis of gradient descent-type methods typically relies on the Lipschitz continuity of the objective gradient. This generally requires an expensive hyperparameter tuning process to appropriately calibrate a stepsize for a given…

最优化与控制 · 数学 2023-11-16 Albert S. Berahas , Lindon Roberts , Fred Roosta

Selecting an effective step-size is a fundamental challenge in first-order optimization, especially for problems with non-Euclidean geometries. This paper presents a novel adaptive step-size strategy for optimization algorithms that rely on…

最优化与控制 · 数学 2025-10-14 Abbas Khademi , Antonio Silveti-Falls

We develop new sub-optimality bounds for gradient descent (GD) that depend on the conditioning of the objective along the path of optimization rather than on global, worst-case constants. Key to our proofs is directional smoothness, a…

机器学习 · 计算机科学 2025-01-15 Aaron Mishkin , Ahmed Khaled , Yuanhao Wang , Aaron Defazio , Robert M. Gower

Adaptive gradient methods are typically used for training over-parameterized models. To better understand their behaviour, we study a simplistic setting -- smooth, convex losses with models over-parameterized enough to interpolate the data.…

机器学习 · 计算机科学 2021-02-22 Sharan Vaswani , Issam Laradji , Frederik Kunstner , Si Yi Meng , Mark Schmidt , Simon Lacoste-Julien

We initiate the study of nonsmooth optimization problems under bounded local subgradient variation, which postulates bounded difference between (sub)gradients in small local regions around points, in either average or maximum sense. The…

最优化与控制 · 数学 2024-11-05 Jelena Diakonikolas , Cristóbal Guzmán

We suggest a simple adaptive step-size procedure, which does not require any line-search, for a general class of nonlinear optimization methods and prove convergence of a general method under mild assumptions. In particular, the goal…

最优化与控制 · 数学 2018-03-05 Igor Konnov

In the development of first-order methods for smooth (resp., composite) convex optimization problems, where smooth functions with Lipschitz continuous gradients are minimized, the gradient (resp., gradient mapping) norm becomes a…

最优化与控制 · 数学 2020-10-06 Masaru Ito , Mituhiro Fukuda
‹ 上一页 1 2 3 10 下一页 ›