English

Error bounds for sparse classifiers in high-dimensions

Statistics Theory 2019-01-15 v3 Statistics Theory

Abstract

We prove an L2 recovery bound for a family of sparse estimators defined as minimizers of some empirical loss functions -- which include hinge loss and logistic loss. More precisely, we achieve an upper-bound for coefficients estimation scaling as (k*/n)\log(p/k*): n,p is the size of the design matrix and k* the dimension of the theoretical loss minimizer. This is done under standard assumptions, for which we derive stronger versions of a cone condition and a restricted strong convexity. Our bound holds with high probability and in expectation and applies to an L1-regularized estimator and to a recently introduced Slope estimator, which we generalize for classification problems. Slope presents the advantage of adapting to unknown sparsity. Thus, we propose a tractable proximal algorithm to compute it and assess its empirical performance. Our results match the best existing bounds for classification and regression problems.

Keywords

Cite

@article{arxiv.1810.03081,
  title  = {Error bounds for sparse classifiers in high-dimensions},
  author = {Antoine Dedieu},
  journal= {arXiv preprint arXiv:1810.03081},
  year   = {2019}
}