Matches in SemOpenAlex for { <https://semopenalex.org/work/W2752017681> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2752017681 abstract "Generalized linear models (GLMs) -- such as logistic regression, Poisson regression, and robust regression -- provide interpretable models for diverse data types. Probabilistic approaches, particularly Bayesian ones, allow coherent estimates of uncertainty, incorporation of prior information, and sharing of power across experiments via hierarchical models. In practice, however, the approximate Bayesian methods necessary for inference have either failed to scale to large data sets or failed to provide theoretical guarantees on the quality of inference. We propose a new approach based on constructing polynomial approximate sufficient statistics for GLMs (PASS-GLM). We demonstrate that our method admits a simple algorithm as well as trivial streaming and distributed extensions that do not compound error across computations. We provide theoretical guarantees on the quality of point (MAP) estimates, the approximate posterior, and posterior mean and uncertainty estimates. We validate our approach empirically in the case of logistic regression using a quadratic approximation and show competitive performance with stochastic gradient descent, MCMC, and the Laplace approximation in terms of speed and multiple measures of accuracy -- including on an advertising data set with 40 million data points and 20,000 covariates." @default.
- W2752017681 created "2017-09-15" @default.
- W2752017681 creator A5007769527 @default.
- W2752017681 creator A5051096462 @default.
- W2752017681 creator A5065653386 @default.
- W2752017681 date "2017-09-26" @default.
- W2752017681 modified "2023-09-27" @default.
- W2752017681 title "PASS-GLM: polynomial approximate sufficient statistics for scalable Bayesian GLM inference" @default.
- W2752017681 cites W1624701674 @default.
- W2752017681 cites W1934021597 @default.
- W2752017681 cites W1964607942 @default.
- W2752017681 cites W2017696952 @default.
- W2752017681 cites W2041836310 @default.
- W2752017681 cites W2059998776 @default.
- W2752017681 cites W2115067168 @default.
- W2752017681 cites W2123395972 @default.
- W2752017681 cites W2146200992 @default.
- W2752017681 cites W2166851633 @default.
- W2752017681 cites W2167433878 @default.
- W2752017681 cites W2279006818 @default.
- W2752017681 cites W2280655926 @default.
- W2752017681 cites W2305001871 @default.
- W2752017681 cites W2404724429 @default.
- W2752017681 cites W2949442184 @default.
- W2752017681 cites W2950204717 @default.
- W2752017681 cites W2950968671 @default.
- W2752017681 cites W2951057540 @default.
- W2752017681 cites W2962709771 @default.
- W2752017681 cites W2963139764 @default.
- W2752017681 cites W2963275203 @default.
- W2752017681 cites W2963649795 @default.
- W2752017681 cites W2963942415 @default.
- W2752017681 cites W3007431310 @default.
- W2752017681 cites W3038165843 @default.
- W2752017681 cites W568673721 @default.
- W2752017681 hasPublicationYear "2017" @default.
- W2752017681 type Work @default.
- W2752017681 sameAs 2752017681 @default.
- W2752017681 citedByCount "0" @default.
- W2752017681 crossrefType "posted-content" @default.
- W2752017681 hasAuthorship W2752017681A5007769527 @default.
- W2752017681 hasAuthorship W2752017681A5051096462 @default.
- W2752017681 hasAuthorship W2752017681A5065653386 @default.
- W2752017681 hasConcept C100906024 @default.
- W2752017681 hasConcept C105795698 @default.
- W2752017681 hasConcept C107673813 @default.
- W2752017681 hasConcept C154945302 @default.
- W2752017681 hasConcept C160234255 @default.
- W2752017681 hasConcept C22243797 @default.
- W2752017681 hasConcept C2776214188 @default.
- W2752017681 hasConcept C33923547 @default.
- W2752017681 hasConcept C37903108 @default.
- W2752017681 hasConcept C41008148 @default.
- W2752017681 hasConcept C41587187 @default.
- W2752017681 hasConceptScore W2752017681C100906024 @default.
- W2752017681 hasConceptScore W2752017681C105795698 @default.
- W2752017681 hasConceptScore W2752017681C107673813 @default.
- W2752017681 hasConceptScore W2752017681C154945302 @default.
- W2752017681 hasConceptScore W2752017681C160234255 @default.
- W2752017681 hasConceptScore W2752017681C22243797 @default.
- W2752017681 hasConceptScore W2752017681C2776214188 @default.
- W2752017681 hasConceptScore W2752017681C33923547 @default.
- W2752017681 hasConceptScore W2752017681C37903108 @default.
- W2752017681 hasConceptScore W2752017681C41008148 @default.
- W2752017681 hasConceptScore W2752017681C41587187 @default.
- W2752017681 hasLocation W27520176811 @default.
- W2752017681 hasOpenAccess W2752017681 @default.
- W2752017681 hasPrimaryLocation W27520176811 @default.
- W2752017681 hasRelatedWork W1911375530 @default.
- W2752017681 hasRelatedWork W2032074167 @default.
- W2752017681 hasRelatedWork W2078051489 @default.
- W2752017681 hasRelatedWork W2101169975 @default.
- W2752017681 hasRelatedWork W2116416291 @default.
- W2752017681 hasRelatedWork W2136097307 @default.
- W2752017681 hasRelatedWork W2156984627 @default.
- W2752017681 hasRelatedWork W2619017672 @default.
- W2752017681 hasRelatedWork W2796180279 @default.
- W2752017681 hasRelatedWork W2904421986 @default.
- W2752017681 hasRelatedWork W2951237533 @default.
- W2752017681 hasRelatedWork W2963303935 @default.
- W2752017681 hasRelatedWork W2964004456 @default.
- W2752017681 hasRelatedWork W2990573086 @default.
- W2752017681 hasRelatedWork W3044699341 @default.
- W2752017681 hasRelatedWork W3086988147 @default.
- W2752017681 hasRelatedWork W3123961406 @default.
- W2752017681 hasRelatedWork W3164193984 @default.
- W2752017681 hasRelatedWork W48075682 @default.
- W2752017681 hasRelatedWork W659047436 @default.
- W2752017681 isParatext "false" @default.
- W2752017681 isRetracted "false" @default.
- W2752017681 magId "2752017681" @default.
- W2752017681 workType "article" @default.