Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963241279> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2963241279 endingPage "3793" @default.
- W2963241279 startingPage "3782" @default.
- W2963241279 abstract "Mean embeddings provide an extremely flexible and powerful tool in machine learning and statistics to represent probability distributions and define a semi-metric (MMD, maximum mean discrepancy ; also called N-distance or energy distance), with numerous successful applications. The representation is constructed as the expectation of the feature map defined by a kernel. As a mean, its classical empirical estimator, however, can be arbitrary severely affected even by a single outlier in case of unbounded features. To the best of our knowledge, unfortunately even the consistency of the existing few techniques trying to alleviate this serious sensitivity bottleneck is unknown. In this paper, we show how the recently emerged principle of median-of-means can be used to design minimax-optimal estimators for kernel mean embedding and MMD, with finite-sample strong outlier-robustness guarantees." @default.
- W2963241279 created "2019-07-30" @default.
- W2963241279 creator A5000295817 @default.
- W2963241279 creator A5024692632 @default.
- W2963241279 creator A5044512769 @default.
- W2963241279 creator A5055231167 @default.
- W2963241279 date "2018-02-09" @default.
- W2963241279 modified "2023-09-29" @default.
- W2963241279 title "MONK – Outlier-Robust Mean Embedding Estimation by Median-of-Means" @default.
- W2963241279 hasPublicationYear "2018" @default.
- W2963241279 type Work @default.
- W2963241279 sameAs 2963241279 @default.
- W2963241279 citedByCount "2" @default.
- W2963241279 countsByYear W29632412792020 @default.
- W2963241279 countsByYear W29632412792021 @default.
- W2963241279 crossrefType "proceedings-article" @default.
- W2963241279 hasAuthorship W2963241279A5000295817 @default.
- W2963241279 hasAuthorship W2963241279A5024692632 @default.
- W2963241279 hasAuthorship W2963241279A5044512769 @default.
- W2963241279 hasAuthorship W2963241279A5055231167 @default.
- W2963241279 hasConcept C104317684 @default.
- W2963241279 hasConcept C105795698 @default.
- W2963241279 hasConcept C11413529 @default.
- W2963241279 hasConcept C118615104 @default.
- W2963241279 hasConcept C126255220 @default.
- W2963241279 hasConcept C149728462 @default.
- W2963241279 hasConcept C153180895 @default.
- W2963241279 hasConcept C154945302 @default.
- W2963241279 hasConcept C162324750 @default.
- W2963241279 hasConcept C176217482 @default.
- W2963241279 hasConcept C185429906 @default.
- W2963241279 hasConcept C185592680 @default.
- W2963241279 hasConcept C21547014 @default.
- W2963241279 hasConcept C33923547 @default.
- W2963241279 hasConcept C41008148 @default.
- W2963241279 hasConcept C41608201 @default.
- W2963241279 hasConcept C55493867 @default.
- W2963241279 hasConcept C63479239 @default.
- W2963241279 hasConcept C67226441 @default.
- W2963241279 hasConcept C74193536 @default.
- W2963241279 hasConcept C79337645 @default.
- W2963241279 hasConceptScore W2963241279C104317684 @default.
- W2963241279 hasConceptScore W2963241279C105795698 @default.
- W2963241279 hasConceptScore W2963241279C11413529 @default.
- W2963241279 hasConceptScore W2963241279C118615104 @default.
- W2963241279 hasConceptScore W2963241279C126255220 @default.
- W2963241279 hasConceptScore W2963241279C149728462 @default.
- W2963241279 hasConceptScore W2963241279C153180895 @default.
- W2963241279 hasConceptScore W2963241279C154945302 @default.
- W2963241279 hasConceptScore W2963241279C162324750 @default.
- W2963241279 hasConceptScore W2963241279C176217482 @default.
- W2963241279 hasConceptScore W2963241279C185429906 @default.
- W2963241279 hasConceptScore W2963241279C185592680 @default.
- W2963241279 hasConceptScore W2963241279C21547014 @default.
- W2963241279 hasConceptScore W2963241279C33923547 @default.
- W2963241279 hasConceptScore W2963241279C41008148 @default.
- W2963241279 hasConceptScore W2963241279C41608201 @default.
- W2963241279 hasConceptScore W2963241279C55493867 @default.
- W2963241279 hasConceptScore W2963241279C63479239 @default.
- W2963241279 hasConceptScore W2963241279C67226441 @default.
- W2963241279 hasConceptScore W2963241279C74193536 @default.
- W2963241279 hasConceptScore W2963241279C79337645 @default.
- W2963241279 hasLocation W29632412791 @default.
- W2963241279 hasOpenAccess W2963241279 @default.
- W2963241279 hasPrimaryLocation W29632412791 @default.
- W2963241279 hasRelatedWork W1793048902 @default.
- W2963241279 hasRelatedWork W1819200193 @default.
- W2963241279 hasRelatedWork W1975484574 @default.
- W2963241279 hasRelatedWork W2050388238 @default.
- W2963241279 hasRelatedWork W2087950056 @default.
- W2963241279 hasRelatedWork W2158040987 @default.
- W2963241279 hasRelatedWork W2244549531 @default.
- W2963241279 hasRelatedWork W2303243086 @default.
- W2963241279 hasRelatedWork W2525360713 @default.
- W2963241279 hasRelatedWork W2773686537 @default.
- W2963241279 hasRelatedWork W2787158631 @default.
- W2963241279 hasRelatedWork W2948712909 @default.
- W2963241279 hasRelatedWork W2964057488 @default.
- W2963241279 hasRelatedWork W2964507278 @default.
- W2963241279 hasRelatedWork W2965465787 @default.
- W2963241279 hasRelatedWork W2973842521 @default.
- W2963241279 hasRelatedWork W3010140118 @default.
- W2963241279 hasRelatedWork W3036786894 @default.
- W2963241279 hasRelatedWork W3196740913 @default.
- W2963241279 hasRelatedWork W3203960595 @default.
- W2963241279 isParatext "false" @default.
- W2963241279 isRetracted "false" @default.
- W2963241279 magId "2963241279" @default.
- W2963241279 workType "article" @default.