English
Related papers

Related papers: A Discrete Variational Derivation of Accelerated M…

200 papers

Arguably, the two most popular accelerated or momentum-based optimization methods in machine learning are Nesterov's accelerated gradient and Polyaks's heavy ball, both corresponding to different discretizations of a particular second order…

Optimization and Control · Mathematics 2020-12-25 Guilherme França , Jeremias Sulam , Daniel P. Robinson , René Vidal

Accelerated gradient methods have had significant impact in machine learning -- in particular the theoretical side of machine learning -- due to their ability to achieve oracle lower bounds. But their heuristic construction has hindered…

Computation · Statistics 2018-02-16 Michael Betancourt , Michael I. Jordan , Ashia C. Wilson

We present two classes of differentially private optimization algorithms derived from the well-known accelerated first-order methods. The first algorithm is inspired by Polyak's heavy ball method and employs a smoothing approach to decrease…

Machine Learning · Computer Science 2022-05-17 Nurdan Kuru , Ş. İlker Birbil , Mert Gurbuzbalaban , Sinan Yildirim

We take a Hamiltonian-based perspective to generalize Nesterov's accelerated gradient descent and Polyak's heavy ball method to a broad class of momentum methods in the setting of (possibly) constrained minimization in Euclidean and…

Optimization and Control · Mathematics 2020-11-17 Jelena Diakonikolas , Michael I. Jordan

Optimization tasks are crucial in statistical machine learning. Recently, there has been great interest in leveraging tools from dynamical systems to derive accelerated and robust optimization methods via suitable discretizations of…

Statistical Mechanics · Physics 2023-07-06 Guilherme França , Alessandro Barp , Mark Girolami , Michael I. Jordan

We aim at computing the derivative of the solution to a parametric optimization problem with respect to the involved parameters. For a class broader than that of strongly convex functions, this can be achieved by automatic differentiation…

Optimization and Control · Mathematics 2019-10-15 Sheheryar Mehmood , Peter Ochs

We use differential equations based approaches to provide some {\it \textbf{physics}} insights into analyzing the dynamics of popular optimization algorithms in machine learning. In particular, we study gradient descent, proximal gradient…

Machine Learning · Computer Science 2018-10-26 Lin F. Yang , R. Arora , V. Braverman , Tuo Zhao

We consider a gradient approximation scheme that is based on applying needle shaped inputs. By using ideas known from the classic proof of the Pontryagin Maximum Principle we derive an approximation that reveals that the considered system…

Systems and Control · Computer Science 2016-03-15 Simon Michalowsky , Christian Ebenbauer

In convex optimization, there is an {\em acceleration} phenomenon in which we can boost the convergence rate of certain gradient-based algorithms. We can observe this phenomenon in Nesterov's accelerated gradient descent, accelerated mirror…

Optimization and Control · Mathematics 2015-09-14 Andre Wibisono , Ashia C. Wilson

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 formulate two classes of first-order algorithms more general than previously studied for minimizing smooth and strongly convex or, respectively, smooth and convex functions. We establish sufficient conditions, via new discrete Lyapunov…

Optimization and Control · Mathematics 2023-04-21 Penghui Fu , Zhiqiang Tan

Recently, continuous-time dynamical systems have proved useful in providing conceptual and quantitative insights into gradient-based optimization, widely used in modern machine learning and statistics. An important question that arises in…

Optimization and Control · Mathematics 2021-04-29 Guilherme França , Michael I. Jordan , René Vidal

Momentum methods play a significant role in optimization. Examples include Nesterov's accelerated gradient method and the conditional gradient algorithm. Several momentum methods are provably optimal under standard oracle models, and all…

Optimization and Control · Mathematics 2018-03-13 Ashia C. Wilson , Benjamin Recht , Michael I. Jordan

We present a unifying framework for adapting the update direction in gradient-based iterative optimization methods. As natural special cases we re-derive classical momentum and Nesterov's accelerated gradient method, lending a new intuitive…

Machine Learning · Statistics 2016-07-12 Aleksandar Botev , Guy Lever , David Barber

In this thesis we develop a novel framework to study smooth and strongly convex optimization algorithms, both deterministic and stochastic. Focusing on quadratic functions we are able to examine optimization algorithms as a recursive…

Optimization and Control · Mathematics 2014-10-24 Yossi Arjevani

This paper delves into the investigation of a distributed aggregative optimization problem within a network. In this scenario, each agent possesses its own local cost function, which relies not only on the local state variable but also on…

Optimization and Control · Mathematics 2025-04-01 Jiaxu Liu , Song Chen , Shengze Cai , Chao Xu , Jian Chu

A variational formulation of accelerated optimization on normed spaces was recently introduced by considering a specific family of time-dependent Bregman Lagrangian and Hamiltonian systems whose corresponding trajectories converge to the…

Optimization and Control · Mathematics 2022-01-11 Valentin Duruisseaux , Melvin Leok

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. This point of view covers the stochastic gradient…

Machine Learning · Statistics 2019-05-08 Andrei Kulunchakov , Julien Mairal

Treating optimization methods as dynamical systems can be traced back centuries ago in order to comprehend the notions and behaviors of optimization methods. Lately, this mind set has become the driving force to design new optimization…

Optimization and Control · Mathematics 2019-09-24 Arman Sharifi Kolarijani , Peyman Mohajerin Esfahani , Tamás Keviczky

Gradient-based optimization algorithms can be studied from the perspective of limiting ordinary differential equations (ODEs). Motivated by the fact that existing ODEs do not distinguish between two fundamentally different…

Optimization and Control · Mathematics 2018-11-05 Bin Shi , Simon S. Du , Michael I. Jordan , Weijie J. Su
‹ Prev 1 2 3 10 Next ›