Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Florea, Mihai I."'
Autor:
Florea, Mihai I.
The gradient mapping norm is a strong and easily verifiable stopping criterion for first-order methods on composite problems. When the objective exhibits the quadratic growth property, the gradient mapping norm minimization problem can be solved by o
Externí odkaz:
http://arxiv.org/abs/2410.23135
Autor:
Florea, Mihai I.
The Optimized Gradient Method (OGM), its strongly convex extension, the Information Theoretical Exact Method (ITEM), as well as the related Triple Momentum Method (TMM) have superior convergence guarantees when compared to the Fast Gradient Method bu
Externí odkaz:
http://arxiv.org/abs/2405.07926
Autor:
Florea, Mihai I., Nesterov, Yurii
First order methods endowed with global convergence guarantees operate using global lower bounds on the objective. The tightening of the bounds has been shown to increase both the theoretical guarantees and the practical performance. In this work, we
Externí odkaz:
http://arxiv.org/abs/2404.18889
Autor:
Florea, Mihai I.
The recently introduced Gradient Methods with Memory use a subset of the past oracle information to create an accurate model of the objective function that enables them to surpass the Gradient Method in practical performance. The model introduces an
Externí odkaz:
http://arxiv.org/abs/2203.07318
Autor:
Nesterov, Yurii, Florea, Mihai I.
Publikováno v:
Optimization Methods and Software (2021), pp. 1-18
In this paper, we consider gradient methods for minimizing smooth convex functions, which employ the information obtained at the previous iterations in order to accelerate the convergence towards the optimal solution. This information is used in the
Externí odkaz:
http://arxiv.org/abs/2105.09241
Publikováno v:
IEEE Signal Processing Letters, vol. 25, no. 7, pp. 961-965, July 2018
Existing ultrasound deconvolution approaches unrealistically assume, primarily for computational reasons, that the convolution model relies on a spatially invariant kernel and circulant boundary conditions. We discard both restrictions and introduce
Externí odkaz:
http://arxiv.org/abs/1801.08479
Autor:
Florea, Mihai I., Vorobyov, Sergiy A.
Publikováno v:
IEEE Trans. Signal Processing, vol. 68, pp. 3033-3048, 2020
The most popular first-order accelerated black-box methods for solving large-scale convex optimization problems are the Fast Gradient Method (FGM) and the Fast Iterative Shrinkage Thresholding Algorithm (FISTA). FGM requires that the objective be fin
Externí odkaz:
http://arxiv.org/abs/1705.10266
Autor:
Florea, Mihai I., Vorobyov, Sergiy A.
Publikováno v:
IEEE Trans. Signal Processing, vol. 67, no. 2, pp. 444-459, Jan. 2019
We introduce a framework, which we denote as the augmented estimate sequence, for deriving fast algorithms with provable convergence guarantees. We use this framework to construct a new first-order scheme, the Accelerated Composite Gradient Method (A
Externí odkaz:
http://arxiv.org/abs/1612.02352
Autor:
Florea, Mihai I.1,2 (AUTHOR) mihai.florea@unitbv.ro
Publikováno v:
Optimization Methods & Software. Dec2022, Vol. 37 Issue 6, p2324-2351. 28p.
Autor:
Nesterov, Yurii1 (AUTHOR), Florea, Mihai I.2 (AUTHOR) mihai.florea@uclouvain.be
Publikováno v:
Optimization Methods & Software. Jun2022, Vol. 37 Issue 3, p936-953. 18p.