Zobrazeno 1 - 10
of 35 101
pro vyhledávání: '"LUCCHI, A."'
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
This paper conducts a comprehensive study of the learning curves of kernel ridge regression (KRR) under minimal assumptions. Our contributions are three-fold: 1) we analyze the role of key properties of the kernel, such as its spectral eigen-decay, t
Externí odkaz:
http://arxiv.org/abs/2410.17796
Optimization methods play a crucial role in modern machine learning, powering the remarkable empirical achievements of deep learning models. These successes are even more remarkable given the complex non-convex nature of the loss landscape of these m
Externí odkaz:
http://arxiv.org/abs/2410.12455
Autor:
Szerszeń, Tomasz
Publikováno v:
Konteksty / Contexts. 308(1-2):407-413
Externí odkaz:
https://www.ceeol.com/search/article-detail?id=343146
This paper addresses the optimization problem of minimizing non-convex continuous functions, which is relevant in the context of high-dimensional machine learning applications characterized by over-parametrization. We analyze a randomized coordinate
Externí odkaz:
http://arxiv.org/abs/2406.16666
Publikováno v:
Il Foro Italiano, 2014 Oct 01. 137(10), 507/508-509/510.
Externí odkaz:
https://www.jstor.org/stable/44880582
Autor:
Marco Bertozzi
Publikováno v:
Cinergie, Vol 4, Iss 8, Pp 7-11 (2015)
Yervant Gianikian and Angela Ricci Lucchi’s cinema uses the images of the past to build knowledge of the contemporary processes. Through the creative force of these authors, ancient images explode with new meanings, often contrary to what the image
Externí odkaz:
https://doaj.org/article/721fb5630e034d669148b5c618f0152f
Autor:
Compagnoni, Enea Monzio, Orvieto, Antonio, Kersting, Hans, Proske, Frank Norbert, Lucchi, Aurelien
Minimax optimization problems have attracted a lot of attention over the past few years, with applications ranging from economics to machine learning. While advanced optimization methods exist for such problems, characterizing their dynamics in stoch
Externí odkaz:
http://arxiv.org/abs/2402.12508
We derive new bounds for the condition number of kernel matrices, which we then use to enhance existing non-asymptotic test error bounds for kernel ridgeless regression (KRR) in the over-parameterized regime for a fixed input dimension. For kernels w
Externí odkaz:
http://arxiv.org/abs/2402.01297
Autor:
Carbone, L.
Publikováno v:
Il Foro Italiano, 2012 Oct 01. 135(10), 2627/2628-2631/2632.
Externí odkaz:
https://www.jstor.org/stable/26639036