Decomposable norm minimization with proximal-gradient homotopy algorithm
نویسندگان
چکیده
منابع مشابه
Decomposable norm minimization with proximal-gradient homotopy algorithm
We study the convergence rate of the proximal-gradient homotopy algorithm applied to normregularized linear least squares problems, for a general class of norms. The homotopy algorithm reduces the regularization parameter in a series of steps, and uses a proximal-gradient algorithm to solve the problem at each step. Proximal-gradient algorithm has a linear rate of convergence given that the obj...
متن کاملScalable Nuclear-norm Minimization by Subspace Pursuit Proximal Riemannian Gradient
Trace-norm regularization plays a vital role in many learning tasks, such as low-rank matrix recovery (MR), and low-rank representation (LRR). Solving this problem directly can be computationally expensive due to the unknown rank of variables or large-rank singular value decompositions (SVDs). To address this, we propose a proximal Riemannian gradient (PRG) scheme which can efficiently solve tr...
متن کاملA Nuclear Norm Minimization Algorithm with Application
In this paper we present a new algorithm to reconstruct prestack (5D) seismic data. If one considers seismic data at a given frequency and, for instance, in the x midpoint, y midpoint, offset and azimuth domain, the data volume can be represented via a 4th order tensor. Seismic data reconstruction can be posed as a tensor completion problem where it is assumed that the fully sampled data can be...
متن کاملThe proximal-proximal gradient algorithm
We consider the problem of minimizing a convex objective which is the sum of a smooth part, with Lipschitz continuous gradient, and a nonsmooth part. Inspired by various applications, we focus on the case when the nonsmooth part is a composition of a proper closed convex function P and a nonzero affine map, with the proximal mappings of τP , τ > 0, easy to compute. In this case, a direct applic...
متن کاملInexact Accelerated Proximal Gradient Algorithms For Matrix l2,1-Norm Minimization Problem in Multi-Task Feature Learning
In this paper, we extend the implementable APG method to solve the matrix l2,1-norm minimization problem arising in multi-task feature learning. We investigate that the resulting inner subproblem has closed-form solution which can be easily determined by taking the problem’s favorable structures. Under suitable conditions, we can establish a comprehensive convergence result for the proposed met...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Computational Optimization and Applications
سال: 2016
ISSN: 0926-6003,1573-2894
DOI: 10.1007/s10589-016-9871-8