2013 NIPS NeurIPS 2013

On model selection consistency of penalized M-estimators: a geometric theory

Abstract

Penalized M-estimators are used in diverse areas of science and engineering to fit high-dimensional models with some low-dimensional structure. Often, the penalties are \emph{geometrically decomposable}, \ie\ can be expressed as a sum of (convex) support functions. We generalize the notion of irrepresentable to geometrically decomposable penalties and develop a general framework for establishing consistency and model selection consistency of M-estimators with such penalties. We then use this framework to derive results for some special cases of interest in bioinformatics and statistical learning.

🌉 Interdisciplinary Bridge — Machine Learning and Mathematics & Optimization
🧭 Keyword Pioneer — model selection consistency
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Data Science & Analytics, Deep Learning, Interdisciplinary, Machine Learning, Mathematics & Optimization, Security & Privacy
📈 Trend Setter — Sparse Optimization
🐣 Hot Topic Early Bird — learning theory