Zobrazeno 1 - 10
of 85
pro vyhledávání: '"BRUGIAPAGLIA, SIMONE"'
In this paper we prove the existence of H\"{o}lder continuous terminal embeddings of any desired $X \subseteq \mathbb{R}^d$ into $\mathbb{R}^{m}$ with $m=\mathcal{O}(\varepsilon^{-2}\omega(S_X)^2)$, for arbitrarily small distortion $\varepsilon$, whe
Externí odkaz:
http://arxiv.org/abs/2408.02812
On the forefront of scientific computing, Deep Learning (DL), i.e., machine learning with Deep Neural Networks (DNNs), has emerged a powerful new tool for solving Partial Differential Equations (PDEs). It has been observed that DNNs are particularly
Externí odkaz:
http://arxiv.org/abs/2406.01539
Dynamic Mode Decomposition (DMD) is a numerical method that seeks to fit timeseries data to a linear dynamical system. In doing so, DMD decomposes dynamic data into spatially coherent modes that evolve in time according to exponential growth/decay or
Externí odkaz:
http://arxiv.org/abs/2405.05057
Learning approximations to smooth target functions of many variables from finite sets of pointwise samples is an important task in scientific computing and its many applications in computational science and engineering. Despite well over half a centu
Externí odkaz:
http://arxiv.org/abs/2404.03761
Autor:
Zangrando, Emanuele, Deidda, Piero, Brugiapaglia, Simone, Guglielmi, Nicola, Tudisco, Francesco
Recent work in deep learning has shown strong empirical and theoretical evidence of an implicit low-rank bias: weight matrices in deep networks tend to be approximately low-rank and removing relatively small singular values during training or from av
Externí odkaz:
http://arxiv.org/abs/2402.03991
In recent years, deep learning has gained increasing popularity in the fields of Partial Differential Equations (PDEs) and Reduced Order Modeling (ROM), providing domain practitioners with new powerful data-driven techniques such as Physics-Informed
Externí odkaz:
http://arxiv.org/abs/2402.00435
We study generative compressed sensing when the measurement matrix is randomly subsampled from a unitary matrix (with the DFT as an important special case). It was recently shown that $\textit{O}(kdn\| \boldsymbol{\alpha}\|_{\infty}^{2})$ uniformly r
Externí odkaz:
http://arxiv.org/abs/2310.04984
Graph Neural Networks (GNNs) have emerged as a powerful tool for data-driven learning on various graph domains. They are usually based on a message-passing mechanism and have gained increasing popularity for their intuitive formulation, which is clos
Externí odkaz:
http://arxiv.org/abs/2307.00134
This paper studies well-posedness and parameter sensitivity of the Square Root LASSO (SR-LASSO), an optimization model for recovering sparse solutions to linear inverse problems in finite dimension. An advantage of the SR-LASSO (e.g., over the standa
Externí odkaz:
http://arxiv.org/abs/2303.15588
We propose a class of greedy algorithms for weighted sparse recovery by considering new loss function-based generalizations of Orthogonal Matching Pursuit (OMP). Given a (regularized) loss function, the proposed algorithms alternate the iterative con
Externí odkaz:
http://arxiv.org/abs/2303.00844