Matches in SemOpenAlex for { <https://semopenalex.org/work/W2790145585> ?p ?o ?g. }
- W2790145585 abstract "Abstract 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 generalization bounds, which improve over the current state-of-the-art ones both in terms of constants and rate of convergence. Moreover, we will also prove that some old and new randomized algorithm, show better generalization performances with respect to their non private counterpart, if the DP is exploited for assessing their generalization ability. Results on a series of algorithms and real world problems show the practical validity of the achieved theoretical results." @default.
- W2790145585 created "2018-03-29" @default.
- W2790145585 creator A5033358562 @default.
- W2790145585 creator A5036611143 @default.
- W2790145585 creator A5045802198 @default.
- W2790145585 creator A5072692847 @default.
- W2790145585 date "2018-07-01" @default.
- W2790145585 modified "2023-09-25" @default.
- W2790145585 title "Randomized learning: Generalization performance of old and new theoretically grounded algorithms" @default.
- W2790145585 cites W1554663460 @default.
- W2790145585 cites W1579369571 @default.
- W2790145585 cites W1680392829 @default.
- W2790145585 cites W168548896 @default.
- W2790145585 cites W1859987214 @default.
- W2790145585 cites W1926592634 @default.
- W2790145585 cites W1982723861 @default.
- W2790145585 cites W1993717606 @default.
- W2790145585 cites W1995945562 @default.
- W2790145585 cites W1999376700 @default.
- W2790145585 cites W2001238748 @default.
- W2790145585 cites W2006151125 @default.
- W2790145585 cites W2009784682 @default.
- W2790145585 cites W2011876338 @default.
- W2790145585 cites W2014384147 @default.
- W2790145585 cites W2019416442 @default.
- W2790145585 cites W2027595342 @default.
- W2790145585 cites W2033559768 @default.
- W2790145585 cites W2042587503 @default.
- W2790145585 cites W2076063813 @default.
- W2790145585 cites W2082233060 @default.
- W2790145585 cites W2087258353 @default.
- W2790145585 cites W2095705004 @default.
- W2790145585 cites W2106525823 @default.
- W2790145585 cites W2119874464 @default.
- W2790145585 cites W2120173732 @default.
- W2790145585 cites W2129538346 @default.
- W2790145585 cites W2137591261 @default.
- W2790145585 cites W2139338362 @default.
- W2790145585 cites W2148603752 @default.
- W2790145585 cites W2149991487 @default.
- W2790145585 cites W2150434953 @default.
- W2790145585 cites W2163187564 @default.
- W2790145585 cites W2165265965 @default.
- W2790145585 cites W2242728483 @default.
- W2790145585 cites W2302010255 @default.
- W2790145585 cites W2466856990 @default.
- W2790145585 cites W2473418344 @default.
- W2790145585 cites W2490023472 @default.
- W2790145585 cites W2498765815 @default.
- W2790145585 cites W2574179923 @default.
- W2790145585 cites W2587006126 @default.
- W2790145585 cites W2911964244 @default.
- W2790145585 cites W2949395086 @default.
- W2790145585 cites W2951851906 @default.
- W2790145585 cites W2964237819 @default.
- W2790145585 cites W3100743579 @default.
- W2790145585 cites W3104887532 @default.
- W2790145585 doi "https://doi.org/10.1016/j.neucom.2017.10.066" @default.
- W2790145585 hasPublicationYear "2018" @default.
- W2790145585 type Work @default.
- W2790145585 sameAs 2790145585 @default.
- W2790145585 citedByCount "6" @default.
- W2790145585 countsByYear W27901455852018 @default.
- W2790145585 countsByYear W27901455852019 @default.
- W2790145585 countsByYear W27901455852020 @default.
- W2790145585 countsByYear W27901455852021 @default.
- W2790145585 countsByYear W27901455852023 @default.
- W2790145585 crossrefType "journal-article" @default.
- W2790145585 hasAuthorship W2790145585A5033358562 @default.
- W2790145585 hasAuthorship W2790145585A5036611143 @default.
- W2790145585 hasAuthorship W2790145585A5045802198 @default.
- W2790145585 hasAuthorship W2790145585A5072692847 @default.
- W2790145585 hasConcept C107673813 @default.
- W2790145585 hasConcept C11413529 @default.
- W2790145585 hasConcept C117765406 @default.
- W2790145585 hasConcept C119857082 @default.
- W2790145585 hasConcept C134306372 @default.
- W2790145585 hasConcept C151730666 @default.
- W2790145585 hasConcept C154945302 @default.
- W2790145585 hasConcept C162324750 @default.
- W2790145585 hasConcept C177148314 @default.
- W2790145585 hasConcept C207201462 @default.
- W2790145585 hasConcept C23130292 @default.
- W2790145585 hasConcept C2777303404 @default.
- W2790145585 hasConcept C2779343474 @default.
- W2790145585 hasConcept C33923547 @default.
- W2790145585 hasConcept C41008148 @default.
- W2790145585 hasConcept C50522688 @default.
- W2790145585 hasConcept C50644808 @default.
- W2790145585 hasConcept C86803240 @default.
- W2790145585 hasConceptScore W2790145585C107673813 @default.
- W2790145585 hasConceptScore W2790145585C11413529 @default.
- W2790145585 hasConceptScore W2790145585C117765406 @default.
- W2790145585 hasConceptScore W2790145585C119857082 @default.
- W2790145585 hasConceptScore W2790145585C134306372 @default.
- W2790145585 hasConceptScore W2790145585C151730666 @default.
- W2790145585 hasConceptScore W2790145585C154945302 @default.
- W2790145585 hasConceptScore W2790145585C162324750 @default.
- W2790145585 hasConceptScore W2790145585C177148314 @default.
- W2790145585 hasConceptScore W2790145585C207201462 @default.