English

Smooth Strongly Convex Regression

Information Theory 2020-03-03 v1 math.IT Optimization and Control

Abstract

Convex regression (CR) is the problem of fitting a convex function to a finite number of noisy observations of an underlying convex function. CR is important in many domains and one of its workhorses is the non-parametric least square estimator (LSE). Currently, LSE delivers only non-smooth non-strongly convex function estimates. In this paper, leveraging recent results in convex interpolation, we generalize LSE to smooth strongly convex regression problems. The resulting algorithm relies on a convex quadratically constrained quadratic program. We also propose a parallel implementation, which leverages ADMM, that lessens the overall computational complexity to a tight O(n2)O(n^2) for nn observations. Numerical results support our findings.

Keywords

Cite

@article{arxiv.2003.00771,
  title  = {Smooth Strongly Convex Regression},
  author = {Andrea Simonetto},
  journal= {arXiv preprint arXiv:2003.00771},
  year   = {2020}
}

Comments

6 pages, 3 figures

R2 v1 2026-06-23T14:00:00.058Z