Zobrazeno 1 - 10
of 28 962
pro vyhledávání: '"minimum norm"'
We study the convergence properties of Variational Quantum Circuits (VQCs) to investigate how they can differ from their classical counterparts. It is known that a VQC is a linear model in a feature map determined by its architecture. Learning a clas
Externí odkaz:
http://arxiv.org/abs/2411.04940
Autor:
Mura, Raffaele, Floris, Giuseppe, Scionis, Luca, Piras, Giorgio, Pintor, Maura, Demontis, Ambra, Giacinto, Giorgio, Biggio, Battista, Roli, Fabio
Gradient-based attacks are a primary tool to evaluate robustness of machine-learning models. However, many attacks tend to provide overly-optimistic evaluations as they use fixed loss functions, optimizers, step-size schedulers, and default hyperpara
Externí odkaz:
http://arxiv.org/abs/2407.08806
Autor:
Gillis, Nicolas, Sicilia, Stefano
Given two matrices $X,B\in \mathbb{R}^{n\times m}$ and a set $\mathcal{A}\subseteq \mathbb{R}^{n\times n}$, a Procrustes problem consists in finding a matrix $A \in \mathcal{A}$ such that the Frobenius norm of $AX-B$ is minimized. When $\mathcal{A}$
Externí odkaz:
http://arxiv.org/abs/2406.02203
Publikováno v:
Mediterranean J. Math. 21 (2024), 163
We study the set $\operatorname{MA}(X,Y)$ of operators between Banach spaces $X$ and $Y$ that attain their minimum norm, and the set $\operatorname{QMA}(X,Y)$ of operators that quasi attain their minimum norm. We characterize the Radon-Nikodym proper
Externí odkaz:
http://arxiv.org/abs/2405.01302
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Given a proper convex lower semicontinuous function defined on a Hilbert space and whose solution set is supposed nonempty. For attaining a global minimizer when this convex function is continuously differentiable, we approach it by a first-order con
Externí odkaz:
http://arxiv.org/abs/2404.00038
Transfer learning is a critical part of real-world machine learning deployments and has been extensively studied in experimental works with overparameterized neural networks. However, even in the simplest setting of linear regression a notable gap st
Externí odkaz:
http://arxiv.org/abs/2404.00522
Publikováno v:
Thirty-seventh Conference on Neural Information Processing Systems 2023
We investigate how shallow ReLU networks interpolate between known regions. Our analysis shows that empirical risk minimizers converge to a minimum norm interpolant as the number of data points and parameters tends to infinity when a weight decay reg
Externí odkaz:
http://arxiv.org/abs/2311.06138
Autor:
Floris, Giuseppe, Mura, Raffaele, Scionis, Luca, Piras, Giorgio, Pintor, Maura, Demontis, Ambra, Biggio, Battista
Evaluating the adversarial robustness of machine learning models using gradient-based attacks is challenging. In this work, we show that hyperparameter optimization can improve fast minimum-norm attacks by automating the selection of the loss functio
Externí odkaz:
http://arxiv.org/abs/2310.08177