Abstract. 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. 1. Introduction. Th
International audienceBy analyzing accelerated proximal gradient methods under a local quadratic gro...
International audienceIn this paper, we analyze the performance of Lasso-TD, a modification of LSTD ...
International audienceFor composite nonsmooth optimization problems, which are "regular enough", pro...
International audienceIn this paper, we consider a class of Forward–Backward (FB) splitting methods ...
The LASSO regression has been studied extensively in the statistics and signal processing community,...
In optimization, it is known that when the objective functions are strictly convex and well-conditio...
In this paper, we consider the Forward–Backward proximal splitting algorithm to minimize the sum of ...
In this paper, we consider the Forward–Backward proximal splitting algorithm to minimize the sum of ...
International audienceIn this paper, we consider the Forward--Backward proximal splitting algorithm ...
We consider the class of inertial Forward–Backward (iFB) proximal splitting algorithms, to minimize ...
In this paper, we propose a restart scheme for FISTA (Fast Iterative Shrinking-Threshold Algorithm)....
Frank\u2013Wolfe (FW) algorithms have been often proposed over the last few years as efficient solve...
International audienceWe consider the estimation of a function in some ordered finite or infinite di...
International audienceFISTA is a classical optimization algorithm to minimize convex functions. The ...
In this work, we are interested in the famous FISTA algorithm. We show that FISTA is an automatic ge...
International audienceBy analyzing accelerated proximal gradient methods under a local quadratic gro...
International audienceIn this paper, we analyze the performance of Lasso-TD, a modification of LSTD ...
International audienceFor composite nonsmooth optimization problems, which are "regular enough", pro...
International audienceIn this paper, we consider a class of Forward–Backward (FB) splitting methods ...
The LASSO regression has been studied extensively in the statistics and signal processing community,...
In optimization, it is known that when the objective functions are strictly convex and well-conditio...
In this paper, we consider the Forward–Backward proximal splitting algorithm to minimize the sum of ...
In this paper, we consider the Forward–Backward proximal splitting algorithm to minimize the sum of ...
International audienceIn this paper, we consider the Forward--Backward proximal splitting algorithm ...
We consider the class of inertial Forward–Backward (iFB) proximal splitting algorithms, to minimize ...
In this paper, we propose a restart scheme for FISTA (Fast Iterative Shrinking-Threshold Algorithm)....
Frank\u2013Wolfe (FW) algorithms have been often proposed over the last few years as efficient solve...
International audienceWe consider the estimation of a function in some ordered finite or infinite di...
International audienceFISTA is a classical optimization algorithm to minimize convex functions. The ...
In this work, we are interested in the famous FISTA algorithm. We show that FISTA is an automatic ge...
International audienceBy analyzing accelerated proximal gradient methods under a local quadratic gro...
International audienceIn this paper, we analyze the performance of Lasso-TD, a modification of LSTD ...
International audienceFor composite nonsmooth optimization problems, which are "regular enough", pro...