Zobrazeno 1 - 10
of 40
pro vyhledávání: '"Alecsa, Cristian Daniel"'
Autor:
Alecsa, Cristian Daniel
In the present paper we introduce new optimization algorithms for the task of density ratio estimation. More precisely, we consider extending the well-known KMM method using the construction of a suitable loss function, in order to encompass more gen
Externí odkaz:
http://arxiv.org/abs/2309.07887
Autor:
Alecsa, Cristian Daniel
In the present work we propose an unsupervised ensemble method consisting of oblique trees that can address the task of auto-encoding, namely Oblique Forest AutoEncoders (briefly OF-AE). Our method is a natural extension of the eForest encoder introd
Externí odkaz:
http://arxiv.org/abs/2301.00880
Autor:
Alecsa, Cristian Daniel
It is known that adaptive optimization algorithms represent the key pillar behind the rise of the Machine Learning field. In the Optimization literature numerous studies have been devoted to accelerated gradient methods but only recently adaptive ite
Externí odkaz:
http://arxiv.org/abs/2110.08531
Autor:
Alecsa, Cristian Daniel
In this paper we propose new numerical algorithms in the setting of unconstrained optimization problems and we study the rate of convergence in the iterates of the objective function. Furthermore, our algorithms are based upon splitting and symplecti
Externí odkaz:
http://arxiv.org/abs/2001.10831
In this paper we deal with a general second order continuous dynamical system associated to a convex minimization problem with a Fr\`echet differentiable objective function. We show that inertial algorithms, such as Nesterov's algorithm, can be obtai
Externí odkaz:
http://arxiv.org/abs/1908.02574
Autor:
Alecsa, Cristian Daniel
It is well known that fixed point problems of contractive-type mappings defined on cone metric spaces over Banach algebras are not equivalent to those in usual metric spaces (see [3] and [10]). In this framework, the novelty of the present paper repr
Externí odkaz:
http://arxiv.org/abs/1906.06261
In the following paper we present a new type of optimization algorithms adapted for neural network training. These algorithms are based upon sequential operator splitting technique for some associated dynamical systems. Furthermore, we investigate th
Externí odkaz:
http://arxiv.org/abs/1904.12952
Publikováno v:
In Neural Networks June 2020 126:178-190
Publikováno v:
Annals of the West University of Timisoara: Mathematics and Computer Science, Vol 57, Iss 1, Pp 23-42 (2019)
In this article, a study of the fixed point problem for Ćirić type multi-valued operators is presented. More precisely, some variants ofĆirić’s contraction principle for multi-valued operators, as well as a strict fixed point principle forĆiri
Externí odkaz:
https://doaj.org/article/f69e513f74c348a49b3aabb86613c98e
Autor:
Alecsa, Cristian Daniel1,2 (AUTHOR), László, Szilárd Csaba3 (AUTHOR) laszlosziszi@yahoo.com, Pinţa, Titus4 (AUTHOR)
Publikováno v:
Applied Mathematics & Optimization. Oct2021, Vol. 84 Issue 2, p1687-1716. 30p.