中文
相关论文

相关论文: A Unified Analysis of First-Order Methods for Smoo…

200 篇论文

This manuscript develops a new framework to analyze and design iterative optimization algorithms built on the notion of Integral Quadratic Constraints (IQC) from robust control theory. IQCs provide sufficient conditions for the stability of…

最优化与控制 · 数学 2021-05-27 Laurent Lessard , Benjamin Recht , Andrew Packard

We develop a unified Lyapunov-integral quadratic constraint (IQC) framework for establishing uniform stability of first-order accelerated optimization algorithms in the $\beta$-smooth and $\gamma$-strongly convex regime. Classical analyses…

最优化与控制 · 数学 2026-05-12 Don Li , Dacian Daescu

The success of adversarial formulations in machine learning has brought renewed motivation for smooth games. In this work, we focus on the class of stochastic Hamiltonian methods and provide the first convergence guarantees for certain…

In this paper, we develop a unified framework able to certify both exponential and subexponential convergence rates for a wide range of iterative first-order optimization algorithms. To this end, we construct a family of parameter-dependent…

最优化与控制 · 数学 2018-02-26 Mahyar Fazlyab , Alejandro Ribeiro , Manfred Morari , Victor M. Preciado

We expose in a tutorial fashion the mechanisms which underlie the synthesis of optimization algorithms based on dynamic integral quadratic constraints. We reveal how these tools from robust control allow to design accelerated gradient…

最优化与控制 · 数学 2023-09-18 Carsten W. Scherer , Christian Ebenbauer , Tobias Holicki

We propose a novel approach for analyzing dynamic regret of first-order constrained online convex optimization algorithms for strongly convex and Lipschitz-smooth objectives. Crucially, we provide a general analysis that is applicable to a…

最优化与控制 · 数学 2025-08-22 Fabian Jakob , Andrea Iannelli

We study the trade-offs between convergence rate and robustness to gradient errors in designing a first-order algorithm. We focus on gradient descent (GD) and accelerated gradient (AG) methods for minimizing strongly convex functions when…

最优化与控制 · 数学 2019-11-07 Necdet Serhat Aybat , Alireza Fallah , Mert Gurbuzbalaban , Asuman Ozdaglar

We introduce a class of first-order methods for smooth constrained optimization that are based on an analogy to non-smooth dynamical systems. Two distinctive features of our approach are that (i) projections or optimizations over the entire…

最优化与控制 · 数学 2025-04-15 Michael Muehlebach , Michael I. Jordan

In this paper, we investigate accelerated first-order methods for smooth convex optimization problems under inexact information on the gradient of the objective. The noise in the gradient is considered to be additive with two possibilities:…

最优化与控制 · 数学 2023-01-10 Vasin Artem , Alexander Gasnikov , Pavel Dvurechensky , Vladimir Spokoiny

This paper presents the Safe Sequential Quadratically Constrained Quadratic Programming (SS-QCQP) algorithm, a first-order method for smooth inequality-constrained nonconvex optimization that guarantees feasibility at every iteration. The…

最优化与控制 · 数学 2025-11-26 Jiarui Wang , Mahyar Fazlyab

Successive quadratic approximations, or second-order proximal methods, are useful for minimizing functions that are a sum of a smooth part and a convex, possibly nonsmooth part that promotes regularization. Most analyses of iteration…

最优化与控制 · 数学 2019-01-25 Ching-pei Lee , Stephen J. Wright

The framework of Integral Quadratic Constraints (IQCs) is used to perform an analysis of gradient descent with varying step sizes. Two performance metrics are considered: convergence rate and noise amplification. We assume that the step…

最优化与控制 · 数学 2025-05-13 Ram Padmanabhan , Peter Seiler

We consider online learning in multi-player smooth monotone games. Existing algorithms have limitations such as (1) being only applicable to strongly monotone games; (2) lacking the no-regret guarantee; (3) having only asymptotic or slow…

机器学习 · 计算机科学 2023-09-06 Yang Cai , Weiqiang Zheng

Iterative gradient-based optimization algorithms are widely used to solve difficult or large-scale optimization problems. There are many algorithms to choose from, such as gradient descent and its accelerated variants such as Polyak's Heavy…

最优化与控制 · 数学 2023-09-21 Bryan Van Scoy , Laurent Lessard

Accelerated first order methods, also called fast gradient methods, are popular optimization methods in the field of convex optimization. However, they are prone to suffer from oscillatory behaviour that slows their convergence when medium…

最优化与控制 · 数学 2022-01-28 Teodoro Alamo , Pablo Krupa , Daniel Limon

This paper optimizes the step coefficients of first-order methods for smooth convex minimization in terms of the worst-case convergence bound (i.e., efficiency) of the decrease in the gradient norm. This work is based on the performance…

最优化与控制 · 数学 2020-10-28 Donghwan Kim , Jeffrey A. Fessler

We establish finite-time last-iterate guarantees for vanilla stochastic gradient descent in co-coercive games under noisy feedback. This is a broad class of games that is more general than strongly monotone games, allows for multiple Nash…

计算机科学与博弈论 · 计算机科学 2026-04-22 Siddharth Chandak , Ramanan Tamizholi , Nicholas Bambos

We consider a class of smooth $N$-player noncooperative games, where player objectives are expectation-valued and potentially nonconvex. In such a setting, we consider the largely open question of efficiently computing a suitably defined…

最优化与控制 · 数学 2025-05-23 Zhuoyu Xiao , Uday V. Shanbhag

The incremental gradient method is a prominent algorithm for minimizing a finite sum of smooth convex functions, used in many contexts including large-scale data processing applications and distributed optimization over networks. It is a…

最优化与控制 · 数学 2022-02-09 Mert Gürbüzbalaban , Asuman Ozdaglar , Pablo Parrilo

We investigate first-order notions of correlated equilibria in smooth games, in which players do not incur any regret against small modifications of their actions prescribed by some vector field. We define two such notions, based on local…

计算机科学与博弈论 · 计算机科学 2025-11-05 Mete Şeref Ahunbay
‹ 上一页 1 2 3 10 下一页 ›