Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Nadiia Chepurko"'
Publikováno v:
FOCS
Recently, Musco and Woodruff (FOCS, 2017) showed that given an $n \times n$ positive semidefinite (PSD) matrix $A$, it is possible to compute a $(1+\epsilon)$-approximate relative-error low-rank approximation to $A$ by querying $O(nk/\epsilon^{2.5})$
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6e16c62de4623bf4e7621a40ed4c8ae8
https://doi.org/10.1109/focs46700.2020.00054
https://doi.org/10.1109/focs46700.2020.00054
Publikováno v:
arXiv
Automatic machine learning (AML) is a family of techniques to automate the process of training predictive models, aiming to both improve performance and make machine learning more accessible. While many recent works have focused on aspects of the mac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9a2c2995c0388669716af527b8d20aa9
http://arxiv.org/abs/2003.09758
http://arxiv.org/abs/2003.09758
Publikováno v:
FOCS
We study the problem of testing whether a matrix $\mathbf{A} \in \mathbb{R}^{n \times n}$ with bounded entries ($\|\mathbf{A}\|_\infty \leq 1$) is positive semi-definite (PSD), or $\epsilon$-far in Euclidean distance from the PSD cone, meaning that $
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::34880b320f6ffda4c5f7bb27f6f71beb