Zobrazeno 1 - 2
of 2
pro vyhledávání: '"65K05, 49M27"'
Autor:
Phan, Anh-Huy, Sobolev, Konstantin, Ermilov, Dmitry, Vorona, Igor, Kozyrskiy, Nikolay, Tichavsky, Petr, Cichocki, Andrzej
A rising problem in the compression of Deep Neural Networks is how to reduce the number of parameters in convolutional kernels and the complexity of these layers by low-rank tensor approximation. Canonical polyadic tensor decomposition (CPD) and Tuck
Externí odkaz:
http://arxiv.org/abs/2203.02617
In this paper, we consider smooth convex optimization problems with simple constraints and inexactness in the oracle information such as value, partial or directional derivatives of the objective function. We introduce a unifying framework, which all
Externí odkaz:
http://arxiv.org/abs/1707.08486