Zobrazeno 1 - 10
of 3 139
pro vyhledávání: '"A. Patrinos"'
This paper presents a novel approach to imitation learning from observations, where an autoregressive mixture of experts model is deployed to fit the underlying policy. The parameters of the model are learned via a two-stage framework. By leveraging
Externí odkaz:
http://arxiv.org/abs/2411.08232
This work introduces an unconventional inexact augmented Lagrangian method, where the augmenting term is a Euclidean norm raised to a power between one and two. The proposed algorithm is applicable to a broad class of constrained nonconvex minimizati
Externí odkaz:
http://arxiv.org/abs/2410.20153
Autor:
Alexopoulos, Theodoros, Maltezos, Stavros, Patrinos, Konstantinos, Iakovidis, George, Koutelieris, George
Resistive strips Micromegas are employed in the ATLAS New Small Wheel project. They have been already installed and operate in the experimental cavern of the ATLAS experiment at CERN. This work attempts to describe the mechanism of the surface electr
Externí odkaz:
http://arxiv.org/abs/2409.19297
We examine stability properties of primal-dual gradient flow dynamics for composite convex optimization problems with multiple, possibly nonsmooth, terms in the objective function under the generalized consensus constraint. The proposed dynamics are
Externí odkaz:
http://arxiv.org/abs/2408.15969
Autor:
Ashtari, Pooya, Behmandpoor, Pourya, Haredasht, Fateme Nateghi, Chen, Jonathan H., Patrinos, Panagiotis, Van Huffel, Sabine
Lossy image compression is essential for efficient transmission and storage. Traditional compression methods mainly rely on discrete cosine transform (DCT) or singular value decomposition (SVD), both of which represent image data in continuous domain
Externí odkaz:
http://arxiv.org/abs/2408.12691
This paper proposes a general switching dynamical system model, and a custom majorization-minimization-based algorithm EM++ for identifying its parameters. For certain families of distributions, such as Gaussian distributions, this algorithm reduces
Externí odkaz:
http://arxiv.org/abs/2407.16359
We consider gradient descent with constant stepsizes and derive exact worst-case convergence rates on the minimum gradient norm of the iterates. Our analysis covers all possible stepsizes and arbitrary upper/lower bounds on the curvature of the objec
Externí odkaz:
http://arxiv.org/abs/2406.17506
Autor:
Tao, Qinghua, Tonin, Francesco, Lambert, Alex, Chen, Yingyi, Patrinos, Panagiotis, Suykens, Johan A. K.
Publikováno v:
the 41st International Conference on Machine Learning (ICML), 2024
In contrast with Mercer kernel-based approaches as used e.g., in Kernel Principal Component Analysis (KPCA), it was previously shown that Singular Value Decomposition (SVD) inherently relates to asymmetric kernels and Asymmetric Kernel Singular Value
Externí odkaz:
http://arxiv.org/abs/2406.08748
We consider a difference-of-convex formulation where one of the terms is allowed to be hypoconvex (or weakly convex). We first examine the precise behavior of a single iteration of the Difference-of-Convex algorithm (DCA), giving a tight characteriza
Externí odkaz:
http://arxiv.org/abs/2403.16864
In this work, we focus on the challenge of transferring an autonomous driving controller from simulation to the real world (i.e. Sim2Real). We propose a data-efficient method for online and on-the-fly adaptation of parametrizable control architecture
Externí odkaz:
http://arxiv.org/abs/2402.16645