Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912371996> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2912371996 abstract "We address the distribution regression problem: we regress from probability measures to Hilbert-space valued outputs, where only samples are available from the input distributions. Many important statistical and machine learning problems can be phrased within this framework including point estimation tasks without analytical solution, or multi-instance learning. However, due to the two-stage sampled nature of the problem, the theoretical analysis becomes quite challenging: to the best of our knowledge the only existing method with performance guarantees requires density estimation (which of ten performs poorly in practise) and the distributions to be defined on a compact Euclidean domain. We present a simple, analytically tractable alternative to solve the distribution regression problem: we embed the distributions to a reproducing kernel Hilbert space and perform ridge regression from the embedded distributions to the outputs. We prove that this scheme is consistent under mild conditions (for distributions on separable topological domains endowed with kernels), and construct explicit finite sample bounds on the excess risk as a function of the sample numbers and the problem difficulty, which hold with high probability. Specifically, we establish the consistency of set kernels in regression, which was a 15-year-old-openquestion, and also present new kernels on embedded distributions. The practical efficiency of the studied technique is illustrated in supervised entropy learning and aerosol prediction using multispectral satellite images." @default.
- W2912371996 created "2019-02-21" @default.
- W2912371996 creator A5004160420 @default.
- W2912371996 creator A5013695358 @default.
- W2912371996 creator A5023198874 @default.
- W2912371996 creator A5044512769 @default.
- W2912371996 date "2015-05-29" @default.
- W2912371996 modified "2023-10-09" @default.
- W2912371996 title "Regression on Probability Measures: A Simple and Consistent Algorithm" @default.
- W2912371996 hasPublicationYear "2015" @default.
- W2912371996 type Work @default.
- W2912371996 sameAs 2912371996 @default.
- W2912371996 citedByCount "0" @default.
- W2912371996 crossrefType "journal-article" @default.
- W2912371996 hasAuthorship W2912371996A5004160420 @default.
- W2912371996 hasAuthorship W2912371996A5013695358 @default.
- W2912371996 hasAuthorship W2912371996A5023198874 @default.
- W2912371996 hasAuthorship W2912371996A5044512769 @default.
- W2912371996 hasConcept C105795698 @default.
- W2912371996 hasConcept C11413529 @default.
- W2912371996 hasConcept C118615104 @default.
- W2912371996 hasConcept C122280245 @default.
- W2912371996 hasConcept C12267149 @default.
- W2912371996 hasConcept C126255220 @default.
- W2912371996 hasConcept C134306372 @default.
- W2912371996 hasConcept C134517425 @default.
- W2912371996 hasConcept C149441793 @default.
- W2912371996 hasConcept C154945302 @default.
- W2912371996 hasConcept C167981619 @default.
- W2912371996 hasConcept C172623408 @default.
- W2912371996 hasConcept C200695384 @default.
- W2912371996 hasConcept C28826006 @default.
- W2912371996 hasConcept C33923547 @default.
- W2912371996 hasConcept C41008148 @default.
- W2912371996 hasConcept C62799726 @default.
- W2912371996 hasConcept C74193536 @default.
- W2912371996 hasConcept C80884492 @default.
- W2912371996 hasConcept C83546350 @default.
- W2912371996 hasConcept C9679016 @default.
- W2912371996 hasConceptScore W2912371996C105795698 @default.
- W2912371996 hasConceptScore W2912371996C11413529 @default.
- W2912371996 hasConceptScore W2912371996C118615104 @default.
- W2912371996 hasConceptScore W2912371996C122280245 @default.
- W2912371996 hasConceptScore W2912371996C12267149 @default.
- W2912371996 hasConceptScore W2912371996C126255220 @default.
- W2912371996 hasConceptScore W2912371996C134306372 @default.
- W2912371996 hasConceptScore W2912371996C134517425 @default.
- W2912371996 hasConceptScore W2912371996C149441793 @default.
- W2912371996 hasConceptScore W2912371996C154945302 @default.
- W2912371996 hasConceptScore W2912371996C167981619 @default.
- W2912371996 hasConceptScore W2912371996C172623408 @default.
- W2912371996 hasConceptScore W2912371996C200695384 @default.
- W2912371996 hasConceptScore W2912371996C28826006 @default.
- W2912371996 hasConceptScore W2912371996C33923547 @default.
- W2912371996 hasConceptScore W2912371996C41008148 @default.
- W2912371996 hasConceptScore W2912371996C62799726 @default.
- W2912371996 hasConceptScore W2912371996C74193536 @default.
- W2912371996 hasConceptScore W2912371996C80884492 @default.
- W2912371996 hasConceptScore W2912371996C83546350 @default.
- W2912371996 hasConceptScore W2912371996C9679016 @default.
- W2912371996 hasLocation W29123719961 @default.
- W2912371996 hasOpenAccess W2912371996 @default.
- W2912371996 hasPrimaryLocation W29123719961 @default.
- W2912371996 hasRelatedWork W2126867230 @default.
- W2912371996 hasRelatedWork W2206086258 @default.
- W2912371996 hasRelatedWork W2284561687 @default.
- W2912371996 hasRelatedWork W2510641838 @default.
- W2912371996 hasRelatedWork W2527716295 @default.
- W2912371996 hasRelatedWork W2774914265 @default.
- W2912371996 hasRelatedWork W2897313170 @default.
- W2912371996 hasRelatedWork W2908620745 @default.
- W2912371996 hasRelatedWork W2935046338 @default.
- W2912371996 hasRelatedWork W2951951091 @default.
- W2912371996 hasRelatedWork W2962862582 @default.
- W2912371996 hasRelatedWork W2963147719 @default.
- W2912371996 hasRelatedWork W2963614384 @default.
- W2912371996 hasRelatedWork W3045027943 @default.
- W2912371996 hasRelatedWork W3100522453 @default.
- W2912371996 hasRelatedWork W3117844572 @default.
- W2912371996 hasRelatedWork W3141627247 @default.
- W2912371996 hasRelatedWork W3170454393 @default.
- W2912371996 hasRelatedWork W3205066492 @default.
- W2912371996 hasRelatedWork W329869691 @default.
- W2912371996 isParatext "false" @default.
- W2912371996 isRetracted "false" @default.
- W2912371996 magId "2912371996" @default.
- W2912371996 workType "article" @default.