Computing a Sparse Projection into a Box

by   Dominique Orban, et al.

We describe a procedure to compute a projection of w ∈ℝ^n into the intersection of the so-called zero-norm ball k 𝔹_0 of radius k, i.e., the set of k-sparse vectors, with a box centered at a point of k 𝔹_0. The need for such projection arises in the context of certain trust-region methods for nonsmooth regularized optimization. Although the set into which we wish to project is nonconvex, we show that a solution may be found in O(n log(n)) operations. We describe our Julia implementation and illustrate our procedure in the context of two trust-region methods for nonsmooth regularized optimization.



page 1

page 2

page 3

page 4


An Iteratively Reweighted Method for Sparse Optimization on Nonconvex ℓ_p Ball

This paper is intended to solve the nonconvex ℓ_p-ball constrained nonli...

Differentiable Trust Region Layers for Deep Reinforcement Learning

Trust region methods are a popular tool in reinforcement learning as the...

A globally convergent method to accelerate topology optimization using on-the-fly model reduction

We present a globally convergent method to accelerate density-based topo...

TREGO: a Trust-Region Framework for Efficient Global Optimization

Efficient Global Optimization (EGO) is the canonical form of Bayesian op...

Faster algorithms for SVP and CVP in the ℓ_∞ norm

Blomer and Naewe[BN09] modified the randomized sieving algorithm of Ajta...

New Computational and Statistical Aspects of Regularized Regression with Application to Rare Feature Selection and Aggregation

Prior knowledge on properties of a target model often come as discrete o...

Effcient Projection Onto the Nonconvex ℓ_p-ball

This paper primarily focuses on computing the Euclidean projection of a ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.