Matches in SemOpenAlex for { <https://semopenalex.org/work/W3019554865> ?p ?o ?g. }
- W3019554865 abstract "We study the problems of learning and testing junta distributions on ${-1,1}^n$ with respect to the uniform distribution, where a distribution $p$ is a $k$-junta if its probability mass function $p(x)$ depends on a subset of at most $k$ variables. The main contribution is an algorithm for finding relevant coordinates in a $k$-junta distribution with subcube conditioning [BC18, CCKLW20]. We give two applications: 1. An algorithm for learning $k$-junta distributions with $tilde{O}(k/epsilon^2) log n + O(2^k/epsilon^2)$ subcube conditioning queries, and 2. An algorithm for testing $k$-junta distributions with $tilde{O}((k + sqrt{n})/epsilon^2)$ subcube conditioning queries. All our algorithms are optimal up to poly-logarithmic factors. Our results show that subcube conditioning, as a natural model for accessing high-dimensional distributions, enables significant savings in learning and testing junta distributions compared to the standard sampling model. This addresses an open question posed by Aliakbarpour, Blais, and Rubinfeld [ABR17]." @default.
- W3019554865 created "2020-05-01" @default.
- W3019554865 creator A5008171524 @default.
- W3019554865 creator A5048454802 @default.
- W3019554865 creator A5049478018 @default.
- W3019554865 creator A5091677337 @default.
- W3019554865 date "2020-04-26" @default.
- W3019554865 modified "2023-09-27" @default.
- W3019554865 title "Learning and Testing Junta Distributions with Subcube Conditioning" @default.
- W3019554865 cites W1479783912 @default.
- W3019554865 cites W1538858266 @default.
- W3019554865 cites W1557882449 @default.
- W3019554865 cites W1570713908 @default.
- W3019554865 cites W1589803317 @default.
- W3019554865 cites W169029076 @default.
- W3019554865 cites W1964857063 @default.
- W3019554865 cites W2002001845 @default.
- W3019554865 cites W2009813398 @default.
- W3019554865 cites W2020584928 @default.
- W3019554865 cites W2021964998 @default.
- W3019554865 cites W2040884411 @default.
- W3019554865 cites W2043356449 @default.
- W3019554865 cites W2073389244 @default.
- W3019554865 cites W2074868939 @default.
- W3019554865 cites W2076381458 @default.
- W3019554865 cites W2104648144 @default.
- W3019554865 cites W2108209146 @default.
- W3019554865 cites W2119479037 @default.
- W3019554865 cites W2132467825 @default.
- W3019554865 cites W2151596305 @default.
- W3019554865 cites W2167101736 @default.
- W3019554865 cites W2170990775 @default.
- W3019554865 cites W2263882035 @default.
- W3019554865 cites W2293110051 @default.
- W3019554865 cites W2293992861 @default.
- W3019554865 cites W2295021037 @default.
- W3019554865 cites W230726820 @default.
- W3019554865 cites W2460522191 @default.
- W3019554865 cites W2465801114 @default.
- W3019554865 cites W2475351935 @default.
- W3019554865 cites W2522428111 @default.
- W3019554865 cites W2586539284 @default.
- W3019554865 cites W2762763087 @default.
- W3019554865 cites W2798303859 @default.
- W3019554865 cites W2798499404 @default.
- W3019554865 cites W2888426597 @default.
- W3019554865 cites W2903158431 @default.
- W3019554865 cites W2914834722 @default.
- W3019554865 cites W2925156518 @default.
- W3019554865 cites W2963245826 @default.
- W3019554865 cites W2963477575 @default.
- W3019554865 cites W2963518214 @default.
- W3019554865 cites W2963597818 @default.
- W3019554865 cites W2963705944 @default.
- W3019554865 cites W2964208417 @default.
- W3019554865 cites W2964252729 @default.
- W3019554865 cites W2964626864 @default.
- W3019554865 cites W2966542271 @default.
- W3019554865 cites W2966565150 @default.
- W3019554865 cites W2972213848 @default.
- W3019554865 cites W2996763839 @default.
- W3019554865 cites W3003993007 @default.
- W3019554865 cites W3013303285 @default.
- W3019554865 hasPublicationYear "2020" @default.
- W3019554865 type Work @default.
- W3019554865 sameAs 3019554865 @default.
- W3019554865 citedByCount "4" @default.
- W3019554865 countsByYear W30195548652020 @default.
- W3019554865 countsByYear W30195548652021 @default.
- W3019554865 crossrefType "posted-content" @default.
- W3019554865 hasAuthorship W3019554865A5008171524 @default.
- W3019554865 hasAuthorship W3019554865A5048454802 @default.
- W3019554865 hasAuthorship W3019554865A5049478018 @default.
- W3019554865 hasAuthorship W3019554865A5091677337 @default.
- W3019554865 hasConcept C105795698 @default.
- W3019554865 hasConcept C110121322 @default.
- W3019554865 hasConcept C11413529 @default.
- W3019554865 hasConcept C114614502 @default.
- W3019554865 hasConcept C118615104 @default.
- W3019554865 hasConcept C134306372 @default.
- W3019554865 hasConcept C14036430 @default.
- W3019554865 hasConcept C33923547 @default.
- W3019554865 hasConcept C39927690 @default.
- W3019554865 hasConcept C41008148 @default.
- W3019554865 hasConcept C45262634 @default.
- W3019554865 hasConcept C63553672 @default.
- W3019554865 hasConcept C78458016 @default.
- W3019554865 hasConcept C86803240 @default.
- W3019554865 hasConceptScore W3019554865C105795698 @default.
- W3019554865 hasConceptScore W3019554865C110121322 @default.
- W3019554865 hasConceptScore W3019554865C11413529 @default.
- W3019554865 hasConceptScore W3019554865C114614502 @default.
- W3019554865 hasConceptScore W3019554865C118615104 @default.
- W3019554865 hasConceptScore W3019554865C134306372 @default.
- W3019554865 hasConceptScore W3019554865C14036430 @default.
- W3019554865 hasConceptScore W3019554865C33923547 @default.
- W3019554865 hasConceptScore W3019554865C39927690 @default.
- W3019554865 hasConceptScore W3019554865C41008148 @default.
- W3019554865 hasConceptScore W3019554865C45262634 @default.
- W3019554865 hasConceptScore W3019554865C63553672 @default.