Zobrazeno 1 - 10
of 55
pro vyhledávání: '"Hien, Le Thi Khanh"'
We propose a Block Majorization Minimization method with Extrapolation (BMMe) for solving a class of multi-convex optimization problems. The extrapolation parameters of BMMe are updated using a novel adaptive update rule. By showing that block majori
Externí odkaz:
http://arxiv.org/abs/2401.06646
Deep Nonnegative Matrix Factorization (deep NMF) has recently emerged as a valuable technique for extracting multiple layers of features across different scales. However, all existing deep NMF models and algorithms have primarily centered their evalu
Externí odkaz:
http://arxiv.org/abs/2309.08249
A significant limitation of one-class classification anomaly detection methods is their reliance on the assumption that unlabeled training data only contains normal instances. To overcome this impractical assumption, we propose two novel classificati
Externí odkaz:
http://arxiv.org/abs/2309.00379
An inertial ADMM for a class of nonconvex composite optimization with nonlinear coupling constraints
In this paper, we propose an inertial alternating direction method of multipliers for solving a class of non-convex multi-block optimization problems with \emph{nonlinear coupling constraints}. Distinctive features of our proposed method, when compar
Externí odkaz:
http://arxiv.org/abs/2212.11336
This paper proposes a multiblock alternating direction method of multipliers for solving a class of multiblock nonsmooth nonconvex optimization problem with nonlinear coupling constraints. We employ a majorization minimization procedure in the update
Externí odkaz:
http://arxiv.org/abs/2201.07657
Publikováno v:
SIAM J. on Mathematics of Data Science 4 (1), pp. 1-25, 2022
In this paper, we consider a class of nonsmooth nonconvex optimization problems whose objective is the sum of a block relative smooth function and a proper and lower semicontinuous block separable function. Although the analysis of block proximal gra
Externí odkaz:
http://arxiv.org/abs/2107.04395
Publikováno v:
Computational Optimization and Applications 83, pp. 247-285, 2022
In this paper, we propose an algorithmic framework, dubbed inertial alternating direction methods of multipliers (iADMM), for solving a class of nonconvex nonsmooth multiblock composite optimization problems with linear constraints. Our framework emp
Externí odkaz:
http://arxiv.org/abs/2102.05433
Publikováno v:
Journal on Machine Learning Research 24 (18), pp. 1-41, 2023
In this paper, we introduce TITAN, a novel inerTIal block majorizaTion minimizAtioN framework for non-smooth non-convex optimization problems. To the best of our knowledge, TITAN is the first framework of block-coordinate update method that relies on
Externí odkaz:
http://arxiv.org/abs/2010.12133
Autor:
Hien, Le Thi Khanh, Gillis, Nicolas
Publikováno v:
Journal of Scientific Computing 87, 93, 2021
Nonnegative matrix factorization (NMF) is a standard linear dimensionality reduction technique for nonnegative data sets. In order to measure the discrepancy between the input data and the low-rank approximation, the Kullback-Leibler (KL) divergence
Externí odkaz:
http://arxiv.org/abs/2010.01935
We propose BIBPA, a block inertial Bregman proximal algorithm for minimizing the sum of a block relatively smooth function (that is, relatively smooth concerning each block) and block separable nonsmooth nonconvex functions. We prove that the sequenc
Externí odkaz:
http://arxiv.org/abs/2003.03963