I-LAMM for sparse learning: simultaneous control of algorithmic complexity and statistical error (Q1750288)
From MaRDI portal
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | I-LAMM for sparse learning: simultaneous control of algorithmic complexity and statistical error |
scientific article |
Statements
I-LAMM for sparse learning: simultaneous control of algorithmic complexity and statistical error (English)
0 references
18 May 2018
0 references
This paper proposes a general computational framework for solving nonconvex optimisation problems such as the penalized M-estimator \(\mathrm{argmin}_{\beta\in{\mathbb R}^d}\{ {\mathcal L}(\beta) + {\mathcal R}_{\lambda}(\beta)\}\), where \({\mathcal L}(\beta)\) is a smooth loss function, \({\mathcal R}_{\lambda}(\beta)\) is a sparsity-inducing penalty with a regularization parameter \(\lambda\). The proposed strategy enables the simultaneous control of the algorithmic complexity and the statistical error when fitting high-dimensional models appearing in various problems including low rank matrix completion problems, high-dimensional graphical models and quantile regression.
0 references
algorithmic statistics
0 references
iteration complexity
0 references
local adaptive MM
0 references
nonconvex statistical optimization
0 references
optimal rate of convergence
0 references
0 references
0 references
0 references
0 references
0 references
0 references
0 references