English
Related papers

Related papers: Understanding the Acceleration Phenomenon via High…

200 papers

Nesterov's accelerated gradient method (NAG) achieves faster convergence than gradient descent for convex optimization but lacks monotonicity in function values. To address this, Beck and Teboulle [2009b] proposed a monotonic variant,…

Optimization and Control · Mathematics 2025-08-06 Mingwei Fu , Bin Shi

In this work, we consider smooth unconstrained optimization problems and we deal with the class of gradient methods with momentum, i.e., descent algorithms where the search direction is defined as a linear combination of the current…

Optimization and Control · Mathematics 2025-12-04 Matteo Lapucci , Giampaolo Liuzzi , Stefano Lucidi , Davide Pucci , Marco Sciandrone

We provide improved convergence rates for various \emph{non-smooth} optimization problems via higher-order accelerated methods. In the case of $\ell_\infty$ regression, we achieves an $O(\epsilon^{-4/5})$ iteration complexity, breaking the…

Optimization and Control · Mathematics 2019-06-05 Brian Bullins , Richard Peng

A wide range of modern science and engineering applications are formulated as optimization problems with a system of partial differential equations (PDEs) as constraints. These PDE-constrained optimization problems are typically solved in a…

Artificial Intelligence · Computer Science 2021-04-28 Yuyu Zhang , Heng Chi , Binghong Chen , Tsz Ling Elaine Tang , Lucia Mirabella , Le Song , Glaucio H. Paulino

Nesterov's accelerated gradient method (NAG) marks a pivotal advancement in gradient-based optimization, achieving faster convergence compared to the vanilla gradient descent method for convex functions. However, its algorithmic complexity…

Optimization and Control · Mathematics 2025-01-21 Mingwei Fu , Bin Shi

We present and analyze a momentum-based gradient method for training linear classifiers with an exponentially-tailed loss (e.g., the exponential or logistic loss), which maximizes the classification margin on separable data at a rate of…

Machine Learning · Computer Science 2021-08-24 Ziwei Ji , Nathan Srebro , Matus Telgarsky

We examine the behavior of accelerated gradient methods in smooth nonconvex unconstrained optimization, focusing in particular on their behavior near strict saddle points. Accelerated methods are iterative methods that typically step along…

Optimization and Control · Mathematics 2018-10-09 Michael O'Neill , Stephen J. Wright

Policy gradient methods are widely used in reinforcement learning algorithms to search for better policies in the parameterized policy space. They do gradient search in the policy space and are known to converge very slowly. Nesterov…

Machine Learning · Computer Science 2018-04-26 K. Lakshmanan

Neural Ordinary Differential Equations (Neural ODEs) represent a significant breakthrough in deep learning, promising to bridge the gap between machine learning and the rich theoretical frameworks developed in various mathematical fields…

Machine Learning · Computer Science 2024-09-24 Jaouad Dabounou

Differentially private (stochastic) gradient descent is the workhorse of DP private machine learning in both the convex and non-convex settings. Without privacy constraints, second-order methods, like Newton's method, converge faster than…

Machine Learning · Computer Science 2023-05-23 Arun Ganesh , Mahdi Haghifam , Thomas Steinke , Abhradeep Thakurta

In this work, we study the computational complexity of reducing the squared gradient magnitude for smooth minimax optimization problems. First, we present algorithms with accelerated $\mathcal{O}(1/k^2)$ last-iterate rates, faster than the…

Optimization and Control · Mathematics 2021-06-11 TaeHo Yoon , Ernest K. Ryu

In this paper, we study the behavior of solutions of the ODE associated to Nesterov acceleration. It is well-known since the pioneering work of Nesterov that the rate of convergence $O(1/t^2)$ is optimal for the class of convex functions…

Optimization and Control · Mathematics 2019-07-09 Jean François Aujol , Charles Dossal , Aude Rondepierre

We introduce two block coordinate descent algorithms for solving optimization problems with ordinary differential equations (ODEs) as dynamical constraints. The algorithms do not need to implement direct or adjoint sensitivity analysis…

Machine Learning · Computer Science 2022-08-30 Ion Matei , Maksym Zhenirovskyy , Johan de Kleer , John Maxwell

In this work, we investigate a second-order dynamical system with Hessian-driven damping tailored for a class of nonconvex functions called strongly quasiconvex. Buil\-ding upon this continuous-time model, we derive two discrete-time…

Optimization and Control · Mathematics 2025-06-19 N. Hadjisavvas , F. Lara , R. T. Marcavillaca , P. T. Vuong

In this paper, we propose a unified view of gradient-based algorithms for stochastic convex composite optimization by extending the concept of estimate sequence introduced by Nesterov. More precisely, we interpret a large class of…

Machine Learning · Statistics 2020-09-07 Andrei Kulunchakov , Julien Mairal

We propose a new unified framework for describing and designing gradient-based convex optimization methods from a numerical analysis perspective. There the key is the new concept of weak discrete gradients (weak DGs), which is a…

Optimization and Control · Mathematics 2023-02-16 Kansei Ushiyama , Shun Sato , Takayasu Matsuo

We propose a general scheme for solving convex and non-convex optimization problems on manifolds. The central idea is that, by adding a multiple of the squared retraction distance to the objective function in question, we "convexify" the…

Computation · Statistics 2020-10-20 Lizhen Lin , Bayan Saparbayeva , Michael Minyi Zhang , David B. Dunson

We present a unifying Nearly Asymptotically Invariant Manifold (NAIM) framework for understanding Nesterovs Accelerated Gradient (NAG) method. By lifting the first-order gradient flow into a second-order phase space we construct a NAIM a…

Systems and Control · Electrical Eng. & Systems 2026-05-01 Rachit Mehra , M Parimi , Amol Yerudkar , S. R. Wagh , Navdeep Singh

This paper considers the decentralized convex optimization problem, which has a wide range of applications in large-scale machine learning, sensor networks, and control theory. We propose novel algorithms that achieve optimal computation…

Machine Learning · Computer Science 2023-10-11 Haishan Ye , Luo Luo , Ziang Zhou , Tong Zhang

In this paper we propose a unified two-phase scheme for convex optimization to accelerate: (1) the adaptive cubic regularization methods with exact/inexact Hessian matrices, and (2) the adaptive gradient method, without any knowledge of the…

Optimization and Control · Mathematics 2017-12-29 Bo Jiang , Tianyi Lin , Shuzhong Zhang