Zobrazeno 1 - 10
of 2 342
pro vyhledávání: '"Lucchi, P"'
The Gauss-Newton (GN) matrix plays an important role in machine learning, most evident in its use as a preconditioning matrix for a wide family of popular adaptive methods to speed up optimization. Besides, it can also provide key insights into the o
Externí odkaz:
http://arxiv.org/abs/2411.02139
Autor:
D'Amelio, Alessandro, Cartella, Giuseppe, Cuculo, Vittorio, Lucchi, Manuele, Cornia, Marcella, Cucchiara, Rita, Boccignone, Giuseppe
Attention guides our gaze to fixate the proper location of the scene and holds it in that location for the deserved amount of time given current processing demands, before shifting to the next one. As such, gaze deployment crucially is a temporal pro
Externí odkaz:
http://arxiv.org/abs/2410.23409
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
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
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
Existing statistical learning guarantees for general kernel regressors often yield loose bounds when used with finite-rank kernels. Yet, finite-rank kernels naturally appear in several machine learning problems, e.g.\ when fine-tuning a pre-trained d
Externí odkaz:
http://arxiv.org/abs/2310.00987
We propose an optimal iterative scheme for federated transfer learning, where a central planner has access to datasets ${\cal D}_1,\dots,{\cal D}_N$ for the same learning model $f_{\theta}$. Our objective is to minimize the cumulative deviation of th
Externí odkaz:
http://arxiv.org/abs/2309.04557
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-19 (2024)
Abstract A multi-disciplinary approach of volcano-stratigraphy, petrology and geochemistry has shed light on the pre-eruptive processes, the eruptive triggering, behaviour and the architecture of the magma plumbing system during the explosive cycle o
Externí odkaz:
https://doaj.org/article/1b02d67a4a044ed3be74ac7bd0591fd7
