High Dimensional Structured Superposition Models

05/30/2017
by   Qilong Gu, et al.
0

High dimensional superposition models characterize observations using parameters which can be written as a sum of multiple component parameters, each with its own structure, e.g., sum of low rank and sparse matrices, sum of sparse and rotated sparse vectors, etc. In this paper, we consider general superposition models which allow sum of any number of component parameters, and each component structure can be characterized by any norm. We present a simple estimator for such models, give a geometric condition under which the components can be accurately estimated, characterize sample complexity of the estimator, and give high probability non-asymptotic bounds on the componentwise estimation error. We use tools from empirical processes and generic chaining for the statistical analysis, and our results, which substantially generalize prior work on superposition models, are in terms of Gaussian widths of suitable sets.

READ FULL TEXT

page 6

page 13

research
06/11/2018

High Dimensional Data Enrichment: Interpretable, Fast, and Data-Efficient

High dimensional structured data enriched model describes groups of obse...
research
06/29/2016

Alternating Estimation for Structured High-Dimensional Multi-Response Models

We consider learning high-dimensional multi-response linear models with ...
research
08/03/2021

High-dimensional changepoint estimation with heterogeneous missingness

We propose a new method for changepoint estimation in partially-observed...
research
02/23/2011

Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions

We analyze a class of estimators based on convex relaxation for solving ...
research
08/14/2022

High-dimensional cointegration and Kuramoto systems

This paper presents a novel estimator for a non-standard restriction to ...
research
04/12/2016

Structured Matrix Recovery via the Generalized Dantzig Selector

In recent years, structured matrix recovery problems have gained conside...
research
01/25/2019

On the Statistical Efficiency of Optimal Kernel Sum Classifiers

We propose a novel combination of optimization tools with learning theor...

Please sign up or login with your details

Forgot password? Click here to reset