Matches in SemOpenAlex for { <https://semopenalex.org/work/W2893061644> ?p ?o ?g. }
- W2893061644 abstract "It is challenging for stochastic optimizations to handle large-scale sensitive data safely. Recently, Duchi et al. proposed private sampling strategy to solve privacy leakage in stochastic optimizations. However, this strategy leads to robustness degeneration, since this strategy is equal to the noise injection on each gradient, which adversely affects updates of the primal variable. To address this challenge, we introduce a robust stochastic optimization under the framework of local privacy, which is called Privacy-pREserving StochasTIc Gradual lEarning (PRESTIGE). PRESTIGE bridges private updates of the primal variable (by private sampling) with the gradual curriculum learning (CL). Specifically, the noise injection leads to the issue of label noise, but the robust learning process of CL can combat with label noise. Thus, PRESTIGE yields private but robust updates of the primal variable on the private curriculum, namely an reordered label sequence provided by CL. In theory, we reveal the convergence rate and maximum complexity of PRESTIGE. Empirical results on six datasets show that, PRESTIGE achieves a good tradeoff between privacy preservation and robustness over baselines." @default.
- W2893061644 created "2018-10-05" @default.
- W2893061644 creator A5010365751 @default.
- W2893061644 creator A5010903591 @default.
- W2893061644 creator A5021751767 @default.
- W2893061644 creator A5047240103 @default.
- W2893061644 creator A5047330894 @default.
- W2893061644 creator A5057762207 @default.
- W2893061644 date "2018-09-30" @default.
- W2893061644 modified "2023-09-27" @default.
- W2893061644 title "Privacy-preserving Stochastic Gradual Learning" @default.
- W2893061644 cites W1873763122 @default.
- W2893061644 cites W1980683432 @default.
- W2893061644 cites W2013823004 @default.
- W2893061644 cites W2019363670 @default.
- W2893061644 cites W2025953099 @default.
- W2893061644 cites W2040263621 @default.
- W2893061644 cites W2052602449 @default.
- W2893061644 cites W2053801139 @default.
- W2893061644 cites W2072566913 @default.
- W2893061644 cites W2112022568 @default.
- W2893061644 cites W2113290770 @default.
- W2893061644 cites W2124940696 @default.
- W2893061644 cites W2127447444 @default.
- W2893061644 cites W2129113961 @default.
- W2893061644 cites W2132984949 @default.
- W2893061644 cites W2138177459 @default.
- W2893061644 cites W2140200142 @default.
- W2893061644 cites W2141012957 @default.
- W2893061644 cites W2146482778 @default.
- W2893061644 cites W2149921886 @default.
- W2893061644 cites W2153635508 @default.
- W2893061644 cites W2160553465 @default.
- W2893061644 cites W2162152253 @default.
- W2893061644 cites W2169150110 @default.
- W2893061644 cites W2169710852 @default.
- W2893061644 cites W2287140434 @default.
- W2893061644 cites W2436219157 @default.
- W2893061644 cites W2610818722 @default.
- W2893061644 cites W2616877139 @default.
- W2893061644 cites W2791759999 @default.
- W2893061644 cites W2950931866 @default.
- W2893061644 cites W2951488730 @default.
- W2893061644 cites W2952265739 @default.
- W2893061644 cites W2953310052 @default.
- W2893061644 cites W2963881987 @default.
- W2893061644 cites W607505555 @default.
- W2893061644 cites W2107204465 @default.
- W2893061644 doi "https://doi.org/10.48550/arxiv.1810.00383" @default.
- W2893061644 hasPublicationYear "2018" @default.
- W2893061644 type Work @default.
- W2893061644 sameAs 2893061644 @default.
- W2893061644 citedByCount "1" @default.
- W2893061644 countsByYear W28930616442019 @default.
- W2893061644 crossrefType "posted-content" @default.
- W2893061644 hasAuthorship W2893061644A5010365751 @default.
- W2893061644 hasAuthorship W2893061644A5010903591 @default.
- W2893061644 hasAuthorship W2893061644A5021751767 @default.
- W2893061644 hasAuthorship W2893061644A5047240103 @default.
- W2893061644 hasAuthorship W2893061644A5047330894 @default.
- W2893061644 hasAuthorship W2893061644A5057762207 @default.
- W2893061644 hasBestOaLocation W28930616441 @default.
- W2893061644 hasConcept C104317684 @default.
- W2893061644 hasConcept C115961682 @default.
- W2893061644 hasConcept C119857082 @default.
- W2893061644 hasConcept C126255220 @default.
- W2893061644 hasConcept C134306372 @default.
- W2893061644 hasConcept C138885662 @default.
- W2893061644 hasConcept C154945302 @default.
- W2893061644 hasConcept C182365436 @default.
- W2893061644 hasConcept C185592680 @default.
- W2893061644 hasConcept C2778329345 @default.
- W2893061644 hasConcept C33923547 @default.
- W2893061644 hasConcept C41008148 @default.
- W2893061644 hasConcept C41895202 @default.
- W2893061644 hasConcept C55493867 @default.
- W2893061644 hasConcept C63479239 @default.
- W2893061644 hasConcept C99498987 @default.
- W2893061644 hasConceptScore W2893061644C104317684 @default.
- W2893061644 hasConceptScore W2893061644C115961682 @default.
- W2893061644 hasConceptScore W2893061644C119857082 @default.
- W2893061644 hasConceptScore W2893061644C126255220 @default.
- W2893061644 hasConceptScore W2893061644C134306372 @default.
- W2893061644 hasConceptScore W2893061644C138885662 @default.
- W2893061644 hasConceptScore W2893061644C154945302 @default.
- W2893061644 hasConceptScore W2893061644C182365436 @default.
- W2893061644 hasConceptScore W2893061644C185592680 @default.
- W2893061644 hasConceptScore W2893061644C2778329345 @default.
- W2893061644 hasConceptScore W2893061644C33923547 @default.
- W2893061644 hasConceptScore W2893061644C41008148 @default.
- W2893061644 hasConceptScore W2893061644C41895202 @default.
- W2893061644 hasConceptScore W2893061644C55493867 @default.
- W2893061644 hasConceptScore W2893061644C63479239 @default.
- W2893061644 hasConceptScore W2893061644C99498987 @default.
- W2893061644 hasLocation W28930616441 @default.
- W2893061644 hasOpenAccess W2893061644 @default.
- W2893061644 hasPrimaryLocation W28930616441 @default.
- W2893061644 hasRelatedWork W2363475415 @default.
- W2893061644 hasRelatedWork W2961085424 @default.
- W2893061644 hasRelatedWork W3046775127 @default.