Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Gupta, Kanan"'
We study the momentum-based minimization of a diffuse perimeter functional on Euclidean spaces and on graphs with applications to semi-supervised classification tasks in machine learning. While the gradient flow in the task at hand is a parabolic par
Externí odkaz:
http://arxiv.org/abs/2501.00389
Autor:
Gupta, Kanan, Wojtowytsch, Stephan
While momentum-based optimization algorithms are commonly used in the notoriously non-convex optimization problems of deep learning, their analysis has historically been restricted to the convex and strongly convex setting. In this article, we partia
Externí odkaz:
http://arxiv.org/abs/2410.08395
We present a generalization of Nesterov's accelerated gradient descent algorithm. Our algorithm (AGNES) provably achieves acceleration for smooth convex and strongly convex minimization tasks with noisy gradient estimates if the noise intensity is pr
Externí odkaz:
http://arxiv.org/abs/2302.05515
Autor:
Miah, Md. Danesh, Akhter, Jarin, Chowdhury, Tamal Kumar, Gupta, Kanan Kumar, Golam Mowla, S.M., Hossain, Md. Akhter
Publikováno v:
In Environmental Challenges December 2021 5
We present a generalization of Nesterov's accelerated gradient descent algorithm. Our algorithm (AGNES) provably achieves acceleration for smooth convex minimization tasks with noisy gradient estimates if the noise intensity is proportional to the ma
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::702b8192ada379b8982f243ed743c987
http://arxiv.org/abs/2302.05515
http://arxiv.org/abs/2302.05515