Work

Conditional Accelerated Lazy Stochastic Gradient Descent

Year: 2017

Type: preprint

Abstract: In this work we introduce a conditional accelerated lazy stochastic gradient descent algorithm with optimal number of calls to a stochastic first-order oracle and convergence rate $O\left(\frac{1}{\varepsilon^2}\right)$ improving over the projection-free, Online Frank-Wolfe based stochastic gradient descent of Hazan and Kale [2012] with convergence rate $O\left(\frac{1}{\varepsilon^4}\right)$.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1703.05840

Authors: Lan, Guanghui, Pokutta, Sebastian, Zhou, Yi, Zink, Daniel

Institution: Georgia Institute of Technology

Language: English

Topic: Stochastic Gradient Optimization Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: National Science Foundation, Office of Naval Research, Division of Civil, Mechanical and Manufacturing Innovation

Awards: G195163794, G3387330441, G353549230, Gradient Sliding Schemes for Large-scale Optimization and Data Analysis, CAREER: Reduced-order Methods for Big-Data Challenges in Nonlinear and Stochastic Optimization, G6671297155, G7923706809, CAREER: Semidefinite Programming (SDP) Extended Formulations, G8876996369

OpenAlex ID: W2602842841

Cites: 20

Cited by: 19

Related to: 10