Matches in SemOpenAlex for { <https://semopenalex.org/work/W3037138603> ?p ?o ?g. }
- W3037138603 abstract "Information-theoretic quantities like entropy and mutual information have found numerous uses in machine learning. It is well known that there is a strong connection between these entropic quantities and submodularity since entropy over a set of random variables is submodular. In this paper, we study combinatorial information measures that generalize independence, (conditional) entropy, (conditional) mutual information, and total correlation defined over sets of (not necessarily random) variables. These measures strictly generalize the corresponding entropic measures since they are all parameterized via submodular functions that themselves strictly generalize entropy. Critically, we show that, unlike entropic mutual information in general, the submodular mutual information is actually submodular in one argument, holding the other fixed, for a large class of submodular functions whose third-order partial derivatives satisfy a non-negativity property. This turns out to include a number of practically useful cases such as the facility location and set-cover functions. We study specific instantiations of the submodular information measures on these, as well as the probabilistic coverage, graph-cut, and saturated coverage functions, and see that they all have mathematically intuitive and practically useful expressions. Regarding applications, we connect the maximization of submodular (conditional) mutual information to problems such as mutual-information-based, query-based, and privacy-preserving summarization -- and we connect optimizing the multi-set submodular mutual information to clustering and robust partitioning." @default.
- W3037138603 created "2020-07-02" @default.
- W3037138603 creator A5000529247 @default.
- W3037138603 creator A5019098931 @default.
- W3037138603 creator A5076905667 @default.
- W3037138603 creator A5091674429 @default.
- W3037138603 date "2020-06-27" @default.
- W3037138603 modified "2023-10-01" @default.
- W3037138603 title "Submodular Combinatorial Information Measures with Applications in Machine Learning" @default.
- W3037138603 cites W108696806 @default.
- W3037138603 cites W1486950299 @default.
- W3037138603 cites W1498671329 @default.
- W3037138603 cites W1574788463 @default.
- W3037138603 cites W1680189815 @default.
- W3037138603 cites W1897230935 @default.
- W3037138603 cites W1910566948 @default.
- W3037138603 cites W1912128066 @default.
- W3037138603 cites W1967051853 @default.
- W3037138603 cites W1989453388 @default.
- W3037138603 cites W1995875735 @default.
- W3037138603 cites W1999824796 @default.
- W3037138603 cites W2011193572 @default.
- W3037138603 cites W2026838540 @default.
- W3037138603 cites W2061820396 @default.
- W3037138603 cites W2061958803 @default.
- W3037138603 cites W2095439994 @default.
- W3037138603 cites W2099111195 @default.
- W3037138603 cites W2109209963 @default.
- W3037138603 cites W2109702961 @default.
- W3037138603 cites W2117659259 @default.
- W3037138603 cites W2118220538 @default.
- W3037138603 cites W2119003693 @default.
- W3037138603 cites W2120173366 @default.
- W3037138603 cites W2125653933 @default.
- W3037138603 cites W2134267347 @default.
- W3037138603 cites W2138597123 @default.
- W3037138603 cites W2139526978 @default.
- W3037138603 cites W2139708568 @default.
- W3037138603 cites W2140678653 @default.
- W3037138603 cites W2144933361 @default.
- W3037138603 cites W2154053567 @default.
- W3037138603 cites W2179494254 @default.
- W3037138603 cites W2225255577 @default.
- W3037138603 cites W2263717697 @default.
- W3037138603 cites W2500139799 @default.
- W3037138603 cites W2556897635 @default.
- W3037138603 cites W2585014550 @default.
- W3037138603 cites W2793673841 @default.
- W3037138603 cites W2809732835 @default.
- W3037138603 cites W2950627537 @default.
- W3037138603 cites W2951482518 @default.
- W3037138603 cites W2953139893 @default.
- W3037138603 cites W2964320283 @default.
- W3037138603 cites W2998052681 @default.
- W3037138603 cites W2310530842 @default.
- W3037138603 hasPublicationYear "2020" @default.
- W3037138603 type Work @default.
- W3037138603 sameAs 3037138603 @default.
- W3037138603 citedByCount "4" @default.
- W3037138603 countsByYear W30371386032020 @default.
- W3037138603 countsByYear W30371386032021 @default.
- W3037138603 crossrefType "posted-content" @default.
- W3037138603 hasAuthorship W3037138603A5000529247 @default.
- W3037138603 hasAuthorship W3037138603A5019098931 @default.
- W3037138603 hasAuthorship W3037138603A5076905667 @default.
- W3037138603 hasAuthorship W3037138603A5091674429 @default.
- W3037138603 hasConcept C101721835 @default.
- W3037138603 hasConcept C106301342 @default.
- W3037138603 hasConcept C114614502 @default.
- W3037138603 hasConcept C121332964 @default.
- W3037138603 hasConcept C124805900 @default.
- W3037138603 hasConcept C126255220 @default.
- W3037138603 hasConcept C152139883 @default.
- W3037138603 hasConcept C15312841 @default.
- W3037138603 hasConcept C154945302 @default.
- W3037138603 hasConcept C177264268 @default.
- W3037138603 hasConcept C178621042 @default.
- W3037138603 hasConcept C199360897 @default.
- W3037138603 hasConcept C2776330181 @default.
- W3037138603 hasConcept C33923547 @default.
- W3037138603 hasConcept C41008148 @default.
- W3037138603 hasConcept C62520636 @default.
- W3037138603 hasConcept C80444323 @default.
- W3037138603 hasConcept C9679016 @default.
- W3037138603 hasConceptScore W3037138603C101721835 @default.
- W3037138603 hasConceptScore W3037138603C106301342 @default.
- W3037138603 hasConceptScore W3037138603C114614502 @default.
- W3037138603 hasConceptScore W3037138603C121332964 @default.
- W3037138603 hasConceptScore W3037138603C124805900 @default.
- W3037138603 hasConceptScore W3037138603C126255220 @default.
- W3037138603 hasConceptScore W3037138603C152139883 @default.
- W3037138603 hasConceptScore W3037138603C15312841 @default.
- W3037138603 hasConceptScore W3037138603C154945302 @default.
- W3037138603 hasConceptScore W3037138603C177264268 @default.
- W3037138603 hasConceptScore W3037138603C178621042 @default.
- W3037138603 hasConceptScore W3037138603C199360897 @default.
- W3037138603 hasConceptScore W3037138603C2776330181 @default.
- W3037138603 hasConceptScore W3037138603C33923547 @default.
- W3037138603 hasConceptScore W3037138603C41008148 @default.
- W3037138603 hasConceptScore W3037138603C62520636 @default.