Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320339577> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4320339577 abstract "We study the problem of estimating the parameters of a Boolean product distribution in $d$ dimensions, when the samples are truncated by a set $S subset {0, 1}^d$ accessible through a membership oracle. This is the first time that the computational and statistical complexity of learning from truncated samples is considered in a discrete setting. We introduce a natural notion of fatness of the truncation set $S$, under which truncated samples reveal enough information about the true distribution. We show that if the truncation set is sufficiently fat, samples from the true distribution can be generated from truncated samples. A stunning consequence is that virtually any statistical task (e.g., learning in total variation distance, parameter estimation, uniformity or identity testing) that can be performed efficiently for Boolean product distributions, can also be performed from truncated samples, with a small increase in sample complexity. We generalize our approach to ranking distributions over $d$ alternatives, where we show how fatness implies efficient parameter estimation of Mallows models from truncated samples. Exploring the limits of learning discrete models from truncated samples, we identify three natural conditions that are necessary for efficient identifiability: (i) the truncation set $S$ should be rich enough; (ii) $S$ should be accessible through membership queries; and (iii) the truncation by $S$ should leave enough randomness in all directions. By carefully adapting the Stochastic Gradient Descent approach of (Daskalakis et al., FOCS 2018), we show that these conditions are also sufficient for efficient learning of truncated Boolean product distributions." @default.
- W4320339577 created "2023-02-13" @default.
- W4320339577 creator A5021246308 @default.
- W4320339577 creator A5027430783 @default.
- W4320339577 creator A5042852153 @default.
- W4320339577 date "2020-07-05" @default.
- W4320339577 modified "2023-09-23" @default.
- W4320339577 title "Efficient Parameter Estimation of Truncated Boolean Product Distributions" @default.
- W4320339577 doi "https://doi.org/10.48550/arxiv.2007.02392" @default.
- W4320339577 hasPublicationYear "2020" @default.
- W4320339577 type Work @default.
- W4320339577 citedByCount "0" @default.
- W4320339577 crossrefType "posted-content" @default.
- W4320339577 hasAuthorship W4320339577A5021246308 @default.
- W4320339577 hasAuthorship W4320339577A5027430783 @default.
- W4320339577 hasAuthorship W4320339577A5042852153 @default.
- W4320339577 hasBestOaLocation W43203395771 @default.
- W4320339577 hasConcept C105795698 @default.
- W4320339577 hasConcept C106195933 @default.
- W4320339577 hasConcept C110121322 @default.
- W4320339577 hasConcept C11413529 @default.
- W4320339577 hasConcept C114614502 @default.
- W4320339577 hasConcept C118615104 @default.
- W4320339577 hasConcept C122770356 @default.
- W4320339577 hasConcept C126255220 @default.
- W4320339577 hasConcept C134306372 @default.
- W4320339577 hasConcept C177264268 @default.
- W4320339577 hasConcept C199360897 @default.
- W4320339577 hasConcept C2524010 @default.
- W4320339577 hasConcept C28826006 @default.
- W4320339577 hasConcept C33923547 @default.
- W4320339577 hasConcept C41008148 @default.
- W4320339577 hasConcept C67499762 @default.
- W4320339577 hasConcept C90673727 @default.
- W4320339577 hasConceptScore W4320339577C105795698 @default.
- W4320339577 hasConceptScore W4320339577C106195933 @default.
- W4320339577 hasConceptScore W4320339577C110121322 @default.
- W4320339577 hasConceptScore W4320339577C11413529 @default.
- W4320339577 hasConceptScore W4320339577C114614502 @default.
- W4320339577 hasConceptScore W4320339577C118615104 @default.
- W4320339577 hasConceptScore W4320339577C122770356 @default.
- W4320339577 hasConceptScore W4320339577C126255220 @default.
- W4320339577 hasConceptScore W4320339577C134306372 @default.
- W4320339577 hasConceptScore W4320339577C177264268 @default.
- W4320339577 hasConceptScore W4320339577C199360897 @default.
- W4320339577 hasConceptScore W4320339577C2524010 @default.
- W4320339577 hasConceptScore W4320339577C28826006 @default.
- W4320339577 hasConceptScore W4320339577C33923547 @default.
- W4320339577 hasConceptScore W4320339577C41008148 @default.
- W4320339577 hasConceptScore W4320339577C67499762 @default.
- W4320339577 hasConceptScore W4320339577C90673727 @default.
- W4320339577 hasLocation W43203395771 @default.
- W4320339577 hasOpenAccess W4320339577 @default.
- W4320339577 hasPrimaryLocation W43203395771 @default.
- W4320339577 hasRelatedWork W1964544637 @default.
- W4320339577 hasRelatedWork W1978042415 @default.
- W4320339577 hasRelatedWork W1980807100 @default.
- W4320339577 hasRelatedWork W2017331178 @default.
- W4320339577 hasRelatedWork W2976797620 @default.
- W4320339577 hasRelatedWork W3038392311 @default.
- W4320339577 hasRelatedWork W3086542228 @default.
- W4320339577 hasRelatedWork W3127301634 @default.
- W4320339577 hasRelatedWork W4232148501 @default.
- W4320339577 hasRelatedWork W4248479957 @default.
- W4320339577 isParatext "false" @default.
- W4320339577 isRetracted "false" @default.
- W4320339577 workType "article" @default.