中文
相关论文

相关论文: Newton methods beyond Hessian Lipschitz continuity…

200 篇论文

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

Finding an $\epsilon$-stationary point of a nonconvex function with a Lipschitz continuous Hessian is a central problem in optimization. Regularized Newton methods are a classical tool and have been studied extensively, yet they still face…

最优化与控制 · 数学 2025-11-03 Yuhao Zhou , Jintao Xu , Bingrui Li , Chenglong Bao , Chao Ding , Jun Zhu

We propose a regularized Hessian-free Newton-type method for minimizing smooth convex functions with Lipschitz continuous Hessians. The algorithm constructs an approximate Hessian by finite differences and selects the regularization…

In this work, we develop first-order (Hessian-free) and zero-order (derivative-free) implementations of the Cubically regularized Newton method for solving general non-convex optimization problems. For that, we employ finite difference…

最优化与控制 · 数学 2023-09-06 Nikita Doikov , Geovani Nunes Grapiglia

We analyze the performance of a variant of Newton method with quadratic regularization for solving composite convex minimization problems. At each step of our method, we choose regularization parameter proportional to a certain power of the…

最优化与控制 · 数学 2022-08-12 Nikita Doikov , Konstantin Mishchenko , Yurii Nesterov

We propose a nonlinear additive Schwarz method for solving nonlinear optimization problems with bound constraints. Our method is used as a "right-preconditioner" for solving the first-order optimality system arising within the sequential…

最优化与控制 · 数学 2024-02-07 Hardik Kothari , Alena Kopaničáková , Rolf Krause

We describe inexact proximal Newton-like methods for solving degenerate regularized optimization problems and for the broader problem of finding a zero of a generalized equation that is the sum of a continuous map and a maximal monotone…

最优化与控制 · 数学 2026-02-12 Ching-pei Lee , Stephen J. Wright

The paper proposes and justifies a new algorithm of the proximal Newton type to solve a broad class of nonsmooth composite convex optimization problems without strong convexity assumptions. Based on advanced notions and techniques of…

最优化与控制 · 数学 2022-03-02 Boris S. Mordukhovich , Xiaoming Yuan , Shangzhi Zeng , Jin Zhang

We analyze nonlinearly preconditioned gradient methods for solving smooth minimization problems. We introduce a generalized smoothness property, based on the notion of abstract convexity, that is broader than Lipschitz smoothness and…

最优化与控制 · 数学 2025-06-18 Konstantinos Oikonomidis , Jan Quan , Emanuel Laude , Panagiotis Patrinos

We show that Newton's method converges globally at a linear rate for objective functions whose Hessians are stable. This class of problems includes many functions which are not strongly convex, such as logistic regression. Our linear…

机器学习 · 计算机科学 2018-06-04 Sai Praneeth Karimireddy , Sebastian U. Stich , Martin Jaggi

We study nonlinearly preconditioned gradient methods for smooth nonconvex optimization problems, focusing on sigmoid preconditioners that inherently perform a form of gradient clipping akin to the widely used gradient clipping technique.…

最优化与控制 · 数学 2025-10-14 Konstantinos Oikonomidis , Jan Quan , Panagiotis Patrinos

A new, fast second-order method is proposed that achieves the optimal $\mathcal{O}\left(|\log(\epsilon)|\epsilon^{-3/2}\right)$ complexity to obtain first-order $\epsilon$-stationary points. Crucially, this is deduced without assuming the…

最优化与控制 · 数学 2026-02-18 Serge Gratton , Sadok Jerad , Philippe L. Toint

We introduce new multilevel methods for solving large-scale unconstrained optimization problems. Specifically, the philosophy of multilevel methods is applied to Newton-type methods that regularize the Newton sub-problem using second order…

最优化与控制 · 数学 2024-07-16 Nick Tsipinakis , Panos Parpas

This work investigates a dynamical system functioning as a nonsmooth adaptation of the continuous Newton method, aimed at minimizing the sum of a primal lower-regular and a locally Lipschitz function, both potentially nonsmooth. The…

最优化与控制 · 数学 2024-12-10 Juan Guillermo Garrido , Pedro Pérez-Aros , Emilio Vilches

Large scale optimization problems are ubiquitous in machine learning and data analysis and there is a plethora of algorithms for solving such problems. Many of these algorithms employ sub-sampling, as a way to either speed up the…

最优化与控制 · 数学 2016-02-29 Farbod Roosta-Khorasani , Michael W. Mahoney

We study generalized smoothness in nonconvex optimization, focusing on $(L_0, L_1)$-smoothness and anisotropic smoothness. The former was empirically derived from practical neural network training examples, while the latter arises naturally…

最优化与控制 · 数学 2025-09-22 Alexander Bodard , Panagiotis Patrinos

We are concerned with a class of nonconvex and nonsmooth composite optimization problems, comprising a twice differentiable function and a prox-regular function. We establish a sufficient condition for the proximal mapping of a prox-regular…

最优化与控制 · 数学 2025-09-09 Yuqia Wu , Pengcheng Wu , Yaohua Hu , Shaohua Pan , Xiaoqi Yang

Second-order methods are provably faster than first-order methods, and their efficient implementations for large-scale optimization problems have attracted significant attention. Yet, optimization problems in ML often have nonsmooth…

最优化与控制 · 数学 2026-02-10 Amal Alphonse , Pavel Dvurechensky , Clemens Sirotenko

Newton's method is the most widespread high-order method, demanding the gradient and the Hessian of the objective function. However, one of the main disadvantages of Newtons method is its lack of global convergence and high iteration cost.…

We analyze Newton's method with lazy Hessian updates for solving general possibly non-convex optimization problems. We propose to reuse a previously seen Hessian for several iterations while computing new gradients at each step of the…

最优化与控制 · 数学 2023-06-16 Nikita Doikov , El Mahdi Chayti , Martin Jaggi
‹ 上一页 1 2 3 10 下一页 ›