Matches in SemOpenAlex for { <https://semopenalex.org/work/W3092139119> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3092139119 abstract "We introduce a framework for online changepoint detection and simultaneous model learning which is applicable to highly parametrized models, such as deep neural networks. It is based on detecting changepoints across time by sequentially performing generalized likelihood ratio tests that require only evaluations of simple prediction score functions. This procedure makes use of checkpoints, consisting of early versions of the actual model parameters, that allow to detect distributional changes by performing predictions on future data. We define an algorithm that bounds the Type I error in the sequential testing procedure. We demonstrate the efficiency of our method in challenging continual learning applications with unknown task changepoints, and show improved performance compared to online Bayesian changepoint detection." @default.
- W3092139119 created "2020-10-15" @default.
- W3092139119 creator A5017255421 @default.
- W3092139119 creator A5033464007 @default.
- W3092139119 creator A5074021977 @default.
- W3092139119 date "2022-03-13" @default.
- W3092139119 modified "2023-10-02" @default.
- W3092139119 title "Sequential changepoint detection in neural networks with checkpoints" @default.
- W3092139119 cites W1967042859 @default.
- W3092139119 cites W1975684011 @default.
- W3092139119 cites W1978129804 @default.
- W3092139119 cites W1989914875 @default.
- W3092139119 cites W1991485860 @default.
- W3092139119 cites W1994616650 @default.
- W3092139119 cites W2036835505 @default.
- W3092139119 cites W2038320902 @default.
- W3092139119 cites W2072372110 @default.
- W3092139119 cites W2091406001 @default.
- W3092139119 cites W2116386744 @default.
- W3092139119 cites W2116522068 @default.
- W3092139119 cites W2117436269 @default.
- W3092139119 cites W2128687162 @default.
- W3092139119 cites W2131036894 @default.
- W3092139119 cites W2141954357 @default.
- W3092139119 cites W2142841946 @default.
- W3092139119 cites W2194775991 @default.
- W3092139119 cites W2473930607 @default.
- W3092139119 cites W2515822248 @default.
- W3092139119 cites W2560647685 @default.
- W3092139119 cites W2919115771 @default.
- W3092139119 cites W2964189064 @default.
- W3092139119 cites W2982701845 @default.
- W3092139119 doi "https://doi.org/10.1007/s11222-022-10088-0" @default.
- W3092139119 hasPublicationYear "2022" @default.
- W3092139119 type Work @default.
- W3092139119 sameAs 3092139119 @default.
- W3092139119 citedByCount "4" @default.
- W3092139119 countsByYear W30921391192020 @default.
- W3092139119 countsByYear W30921391192021 @default.
- W3092139119 countsByYear W30921391192023 @default.
- W3092139119 crossrefType "journal-article" @default.
- W3092139119 hasAuthorship W3092139119A5017255421 @default.
- W3092139119 hasAuthorship W3092139119A5033464007 @default.
- W3092139119 hasAuthorship W3092139119A5074021977 @default.
- W3092139119 hasBestOaLocation W30921391192 @default.
- W3092139119 hasConcept C107673813 @default.
- W3092139119 hasConcept C111472728 @default.
- W3092139119 hasConcept C11413529 @default.
- W3092139119 hasConcept C119857082 @default.
- W3092139119 hasConcept C138885662 @default.
- W3092139119 hasConcept C153180895 @default.
- W3092139119 hasConcept C154945302 @default.
- W3092139119 hasConcept C162324750 @default.
- W3092139119 hasConcept C187736073 @default.
- W3092139119 hasConcept C2780451532 @default.
- W3092139119 hasConcept C2780586882 @default.
- W3092139119 hasConcept C41008148 @default.
- W3092139119 hasConcept C50644808 @default.
- W3092139119 hasConceptScore W3092139119C107673813 @default.
- W3092139119 hasConceptScore W3092139119C111472728 @default.
- W3092139119 hasConceptScore W3092139119C11413529 @default.
- W3092139119 hasConceptScore W3092139119C119857082 @default.
- W3092139119 hasConceptScore W3092139119C138885662 @default.
- W3092139119 hasConceptScore W3092139119C153180895 @default.
- W3092139119 hasConceptScore W3092139119C154945302 @default.
- W3092139119 hasConceptScore W3092139119C162324750 @default.
- W3092139119 hasConceptScore W3092139119C187736073 @default.
- W3092139119 hasConceptScore W3092139119C2780451532 @default.
- W3092139119 hasConceptScore W3092139119C2780586882 @default.
- W3092139119 hasConceptScore W3092139119C41008148 @default.
- W3092139119 hasConceptScore W3092139119C50644808 @default.
- W3092139119 hasIssue "2" @default.
- W3092139119 hasLocation W30921391191 @default.
- W3092139119 hasLocation W30921391192 @default.
- W3092139119 hasOpenAccess W3092139119 @default.
- W3092139119 hasPrimaryLocation W30921391191 @default.
- W3092139119 hasRelatedWork W2081647779 @default.
- W3092139119 hasRelatedWork W2961085424 @default.
- W3092139119 hasRelatedWork W3046775127 @default.
- W3092139119 hasRelatedWork W3170094116 @default.
- W3092139119 hasRelatedWork W4205958290 @default.
- W3092139119 hasRelatedWork W4285260836 @default.
- W3092139119 hasRelatedWork W4286629047 @default.
- W3092139119 hasRelatedWork W4306321456 @default.
- W3092139119 hasRelatedWork W4306674287 @default.
- W3092139119 hasRelatedWork W4224009465 @default.
- W3092139119 hasVolume "32" @default.
- W3092139119 isParatext "false" @default.
- W3092139119 isRetracted "false" @default.
- W3092139119 magId "3092139119" @default.
- W3092139119 workType "article" @default.