Local Linear Convergence of ISTA and FISTA on the LASSO Problem

نویسندگان

  • Shaozhe Tao
  • Daniel Boley
  • Shuzhong Zhang
چکیده

We establish local linear convergence bounds for the ISTA and FISTA iterations on the model LASSO problem. We show that FISTA can be viewed as an accelerated ISTA process. Using a spectral analysis, we show that, when close enough to the solution, both iterations converge linearly, but FISTA slows down compared to ISTA, making it advantageous to switch to ISTA toward the end of the iteration processs. We illustrate the results with some synthetic numerical examples.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Convergence of Common Proximal Methods for 1-Regularized Least Squares

We compare the convergence behavior of ADMM (alternating direction method of multipliers), [F]ISTA ([fast] iterative shrinkage and thresholding algorithm) and CD (coordinate descent) methods on the model `1-regularized least squares problem (aka LASSO). We use an eigenanalysis of the operators to compare their local convergence rates when close to the solution. We find that, when applicable, CD...

متن کامل

Convergence of Common Proximal Methods for L1-Regularized Least Squares

We compare the convergence behavior of ADMM (alternating direction method of multipliers), [F]ISTA ([fast] iterative shrinkage and thresholding algorithm) and CD (coordinate descent) methods on the model `1-regularized least squares problem (aka LASSO). We use an eigenanalysis of the operators to compare their local convergence rates when close to the solution. We find that, when applicable, CD...

متن کامل

Accelerating ISTA with an active set strategy

Starting from a practical implementation of Roth and Fisher’s algorithm to solve a Lasso-type problem, we propose and study the Active Set Iterative Shrinkage/Thresholding Algorithm (AS-ISTA). The convergence is proven by observing that the algorithm can be seen as a particular case of a coordinate gradient descent algorithm with a Gauss-Southwell-r rule. We provide experimental evidence that t...

متن کامل

Convergence Analysis of ISTA and FISTA for “Strongly + Semi” Convex Programming

The iterative shrinkage/thresholding algorithm (ISTA) and its faster version FISTA have been widely used in the literature. In this paper, we consider general versions of the ISTA and FISTA in the more general “strongly + semi” convex setting, i.e., minimizing the sum of a strongly convex function and a semiconvex function; and conduct convergence analysis for them. The consideration of a semic...

متن کامل

Activity Identification and Local Linear Convergence of Forward-Backward-type Methods

In this paper, we consider a class of Forward–Backward (FB) splitting methods that includes several variants (e.g. inertial schemes, FISTA) for minimizing the sum of two proper convex and lower semi-continuous functions, one of which has a Lipschitz continuous gradient, and the other is partly smooth relatively to a smooth active manifoldM. We propose a unified framework, under which we show th...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • SIAM Journal on Optimization

دوره 26  شماره 

صفحات  -

تاریخ انتشار 2016