Perspective Functions: Proximal Calculus and Applications in High-Dimensional Statistics
Preprint
Abstract
Perspective functions arise explicitly or implicitly in various forms in applied mathematics and in statistical data analysis. To date, no systematic strategy is available to solve the associated, typically nonsmooth, optimization problems. In this paper, we fill this gap by showing that proximal methods provide an efficient framework to model and solve problems involving perspective functions. We study the construction of the proximity operator of a perspective function under general assumptions and present important instances in which the proximity operator can be computed explicitly or via straightforward numerical operations. These results constitute central building blocks in the design of proximal optimization algorithms. We showcase the versatility of the framework by designing novel proximal algorithms for state-of-the-art regression and variable selection schemes in high-dimensional statistics.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- Non-Convex Global Minimization and False Discovery Rate Control for the TREXJournal of Computational and Graphical Statistics, 2018
- Proximity Operators of Discrete Information DivergencesIEEE Transactions on Information Theory, 2017
- Efficient Smoothed Concomitant Lasso Estimation for High Dimensional RegressionJournal of Physics: Conference Series, 2017
- Perspective Functions: Properties, Constructions, and ExamplesSet-Valued and Variational Analysis, 2017
- Asynchronous block-iterative primal-dual decomposition methods for monotone inclusionsMathematical Programming, 2016
- Conic Optimization via Operator Splitting and Homogeneous Self-Dual EmbeddingJournal of Optimization Theory and Applications, 2016
- Scaled sparse linear regressionBiometrika, 2012
- Square-root lasso: pivotal recovery of sparse signals via conic programmingBiometrika, 2011
- Sharp Thresholds for High-Dimensional and Noisy Sparsity Recovery Using $\ell _{1}$-Constrained Quadratic Programming (Lasso)IEEE Transactions on Information Theory, 2009
- A robust hybrid of lasso and ridge regression2007