Zobrazeno 1 - 10
of 147
pro vyhledávání: '"Sandro Ridella"'
Autor:
Luca Oneto, Sandro Ridella
Publikováno v:
Entropy, Vol 23, Iss 1, p 101 (2021)
In this paper, we deal with the classical Statistical Learning Theory’s problem of bounding, with high probability, the true risk R(h) of a hypothesis h chosen from a set H of m hypotheses. The Union Bound (UB) allows one to state that PLR^(h),δqh
Externí odkaz:
https://doaj.org/article/2f1ac63c34f44d52b7ae824395f62142
Publikováno v:
Neurocomputing. 543:126227
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::064dbb4b7a214a6b594d86e89dc09258
https://doi.org/10.1016/j.neucom.2023.126227
https://doi.org/10.1016/j.neucom.2023.126227
Publikováno v:
ESANN 2022 proceedings.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::564faf0376036b704ac267638cc7170a
https://doi.org/10.14428/esann/2022.es2022-13
https://doi.org/10.14428/esann/2022.es2022-13
Publikováno v:
Scopus-Elsevier
Support Vector Machines (SVMs) are a state-of-the-art and powerful learning algorithm that can effectively solve many real world problems. SVMs are the transposition of the Vapnik–Chervonenkis (VC) theory into a learning algorithm. In this paper, w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::65a0f711eb5a1659c783a01a7b3f601d
https://doi.org/10.1016/j.neucom.2018.10.087
https://doi.org/10.1016/j.neucom.2018.10.087
Autor:
Sandro Ridella, Luca Oneto
Publikováno v:
Entropy
Volume 23
Issue 1
Entropy, Vol 23, Iss 101, p 101 (2021)
Volume 23
Issue 1
Entropy, Vol 23, Iss 101, p 101 (2021)
In this paper, we deal with the classical Statistical Learning Theory&rsquo
s problem of bounding, with high probability, the true risk R(h) of a hypothesis h chosen from a set H of m hypotheses. The Union Bound (UB) allows one to state that PLR
s problem of bounding, with high probability, the true risk R(h) of a hypothesis h chosen from a set H of m hypotheses. The Union Bound (UB) allows one to state that PLR
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f90551911d3087c021d421def8e8702f
http://europepmc.org/articles/PMC7827710
http://europepmc.org/articles/PMC7827710
In the context of assessing the generalization abilities of a randomized model or learning algorithm, PAC-Bayes and Differential Privacy (DP) theories are the state-of-the-art tools. For this reason, in this paper, we will develop tight DP-based gene
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::635e42f17a50fc4fa9718698021ac150
http://hdl.handle.net/11568/997092
http://hdl.handle.net/11568/997092
Quantum computing represents a promising paradigm for solving complex problems, such as large-number factorization, exhaustive search, optimization, and mean and median computation. On the other hand, supervised learning deals with the classical indu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5440319b103777a38480e1064f4914af
https://doi.org/10.1016/b978-0-12-804409-4.00002-4
https://doi.org/10.1016/b978-0-12-804409-4.00002-4
We derive new Chernoff and Bennett type risk bounds based on Differential Privacy(DP).CDP, a randomized learning algorithm based on the Catonis work, is DP.CDP has better generalization properties than the Catoni based Gibbs classifier.We discuss the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a066c82e38c949057bfc18085358d396
http://hdl.handle.net/11567/881489
http://hdl.handle.net/11567/881489