FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2138855972> ?p ?o ?g. }

• W2138855972 abstract "In this paper, we consider supervised learning problems such as logistic regression and study the stochastic gradient method with averaging, in the usual stochastic approximation setting where observations are used only once. We show that after N iterations, with a constant step-size proportional to 1/R2√N where N is the number of observations and R is the maximum norm of the observations, the convergence rate is always of order O(1/√N), and improves to O(R2/µN) where µ is the lowest eigenvalue of the Hessian at the global optimum (when this eigenvalue is greater than R2/√N. Since µ does not need to be known in advance, this shows that averaged stochastic gradient is adaptive to unknown local strong convexity of the objective function. Our proof relies on the generalized self-concordance properties of the logistic loss and thus extends to all generalized linear models with uniformly bounded features." @default.
• W2138855972 created "2016-06-24" @default.
• W2138855972 creator A5001483226 @default.
• W2138855972 date "2014-01-01" @default.
• W2138855972 modified "2023-10-06" @default.
• W2138855972 title "Adaptivity of averaged stochastic gradient descent to local strong convexity for logistic regression" @default.
• W2138855972 cites W1499021337 @default.
• W2138855972 cites W1505731132 @default.
• W2138855972 cites W1510073064 @default.
• W2138855972 cites W1556545893 @default.
• W2138855972 cites W1632601927 @default.
• W2138855972 cites W1980412153 @default.
• W2138855972 cites W1992208280 @default.
• W2138855972 cites W2022829242 @default.
• W2138855972 cites W2024484010 @default.
• W2138855972 cites W2030811966 @default.
• W2138855972 cites W2066623346 @default.
• W2138855972 cites W2083459869 @default.
• W2138855972 cites W2086161653 @default.
• W2138855972 cites W2095895508 @default.
• W2138855972 cites W2096199223 @default.
• W2138855972 cites W2096840748 @default.
• W2138855972 cites W2100911008 @default.
• W2138855972 cites W2101159990 @default.
• W2138855972 cites W2113651538 @default.
• W2138855972 cites W2120350480 @default.
• W2138855972 cites W2125993116 @default.
• W2138855972 cites W2135106139 @default.
• W2138855972 cites W2138682935 @default.
• W2138855972 cites W2142623206 @default.
• W2138855972 cites W2147880316 @default.
• W2138855972 cites W2151695970 @default.
• W2138855972 cites W2154682027 @default.
• W2138855972 cites W2156779765 @default.
• W2138855972 cites W2159930037 @default.
• W2138855972 cites W2164301055 @default.
• W2138855972 cites W2169713291 @default.
• W2138855972 cites W2294719340 @default.
• W2138855972 cites W2404385938 @default.
• W2138855972 cites W2963981973 @default.
• W2138855972 cites W3023786531 @default.
• W2138855972 cites W3141595720 @default.
• W2138855972 cites W568673721 @default.
• W2138855972 cites W59018853 @default.
• W2138855972 cites W88685657 @default.
• W2138855972 hasPublicationYear "2014" @default.
• W2138855972 type Work @default.
• W2138855972 sameAs 2138855972 @default.
• W2138855972 citedByCount "69" @default.
• W2138855972 countsByYear W21388559722013 @default.
• W2138855972 countsByYear W21388559722014 @default.
• W2138855972 countsByYear W21388559722015 @default.
• W2138855972 countsByYear W21388559722016 @default.
• W2138855972 countsByYear W21388559722017 @default.
• W2138855972 countsByYear W21388559722018 @default.
• W2138855972 countsByYear W21388559722019 @default.
• W2138855972 countsByYear W21388559722020 @default.
• W2138855972 countsByYear W21388559722021 @default.
• W2138855972 countsByYear W21388559722022 @default.
• W2138855972 crossrefType "journal-article" @default.
• W2138855972 hasAuthorship W2138855972A5001483226 @default.
• W2138855972 hasBestOaLocation W21388559721 @default.
• W2138855972 hasConcept C105795698 @default.
• W2138855972 hasConcept C106159729 @default.
• W2138855972 hasConcept C149782125 @default.
• W2138855972 hasConcept C151956035 @default.
• W2138855972 hasConcept C153294291 @default.
• W2138855972 hasConcept C154945302 @default.
• W2138855972 hasConcept C162324750 @default.
• W2138855972 hasConcept C205649164 @default.
• W2138855972 hasConcept C206688291 @default.
• W2138855972 hasConcept C2776637919 @default.
• W2138855972 hasConcept C28826006 @default.
• W2138855972 hasConcept C33923547 @default.
• W2138855972 hasConcept C41008148 @default.
• W2138855972 hasConcept C50644808 @default.
• W2138855972 hasConcept C72134830 @default.
• W2138855972 hasConcept C83546350 @default.
• W2138855972 hasConceptScore W2138855972C105795698 @default.
• W2138855972 hasConceptScore W2138855972C106159729 @default.
• W2138855972 hasConceptScore W2138855972C149782125 @default.
• W2138855972 hasConceptScore W2138855972C151956035 @default.
• W2138855972 hasConceptScore W2138855972C153294291 @default.
• W2138855972 hasConceptScore W2138855972C154945302 @default.
• W2138855972 hasConceptScore W2138855972C162324750 @default.
• W2138855972 hasConceptScore W2138855972C205649164 @default.
• W2138855972 hasConceptScore W2138855972C206688291 @default.
• W2138855972 hasConceptScore W2138855972C2776637919 @default.
• W2138855972 hasConceptScore W2138855972C28826006 @default.
• W2138855972 hasConceptScore W2138855972C33923547 @default.
• W2138855972 hasConceptScore W2138855972C41008148 @default.
• W2138855972 hasConceptScore W2138855972C50644808 @default.
• W2138855972 hasConceptScore W2138855972C72134830 @default.
• W2138855972 hasConceptScore W2138855972C83546350 @default.
• W2138855972 hasLocation W21388559721 @default.
• W2138855972 hasLocation W21388559722 @default.
• W2138855972 hasLocation W21388559723 @default.
• W2138855972 hasLocation W21388559724 @default.
• W2138855972 hasLocation W21388559725 @default.
• W2138855972 hasOpenAccess W2138855972 @default.

• next