A Unified Optimization Framework for Low-Rank Inducing Penalties
From MaRDI portal
Publication:6333359
arXiv2001.08415MaRDI QIDQ6333359FDOQ6333359
Authors: Marcus Valtonen Örnhag, Carl Olsson, Anders Heyden 
Publication date: 23 January 2020
Abstract: In this paper we study the convex envelopes of a new class of functions. Using this approach, we are able to unify two important classes of regularizers from unbiased non-convex formulations and weighted nuclear norm penalties. This opens up for possibilities of combining the best of both worlds, and to leverage each methods contribution to cases where simply enforcing one of the regularizers are insufficient. We show that the proposed regularizers can be incorporated in standard splitting schemes such as Alternating Direction Methods of Multipliers (ADMM), and other subgradient methods. Furthermore, we provide an efficient way of computing the proximal operator. Lastly, we show on real non-rigid structure-from-motion (NRSfM) datasets, the issues that arise from using weighted nuclear norm penalties, and how this can be remedied using our proposed method.
Has companion code repository: https://github.com/marcusvaltonen/UnifiedFramework
This page was built for publication: A Unified Optimization Framework for Low-Rank Inducing Penalties
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6333359)
