Accelerated Gradient Descent Method for Projections onto the ℓ1-Ball
Loading...
Date
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Institute of Electrical and Electronics Engineers
Acceso al texto completo solo para la Comunidad PUCP
Abstract
We present a computationally efficient algorithm to solve the projection onto the ℓ 1 -ball problem, which is cast as an equivalent univariate optimization problem by means of its dual formulation, the ℓ ∞ proximity operator. Our algorithm, which is a customization of the Nesterov's accelerated gradient descent method, is empirically demonstrated to be faster than the state-of-the-art methods for the projection onto the ℓ 1 -ball problem.
Description
Keywords
Ball (mathematics), Gradient descent, Stochastic gradient descent, Algorithm, Projection (relational algebra), Computer science, Univariate, Mathematics, Combinatorics, Artificial intelligence, Multivariate statistics, Mathematical analysis, Machine learning, Artificial neural network