Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376288907> ?p ?o ?g. }
- W4376288907 endingPage "705" @default.
- W4376288907 startingPage "671" @default.
- W4376288907 abstract "In this work we consider stochastic gradient descent (SGD) for solving linear inverse problems in Banach spaces. SGD and its variants have been established as one of the most successful optimization methods in machine learning, imaging, and signal processing, to name a few. At each iteration SGD uses a single datum, or a small subset of data, resulting in highly scalable methods that are very attractive for large-scale inverse problems. Nonetheless, the theoretical analysis of SGD-based approaches for inverse problems has thus far been largely limited to Euclidean and Hilbert spaces. In this work we present a novel convergence analysis of SGD for linear inverse problems in general Banach spaces: we show the almost sure convergence of the iterates to the minimum norm solution and establish the regularizing property for suitable a priori stopping criteria. Numerical results are also presented to illustrate features of the approach." @default.
- W4376288907 created "2023-05-13" @default.
- W4376288907 creator A5039605463 @default.
- W4376288907 creator A5075218826 @default.
- W4376288907 date "2023-05-15" @default.
- W4376288907 modified "2023-09-24" @default.
- W4376288907 title "On the Convergence of Stochastic Gradient Descent for Linear Inverse Problems in Banach Spaces" @default.
- W4376288907 cites W1564864701 @default.
- W4376288907 cites W1570089119 @default.
- W4376288907 cites W1754711404 @default.
- W4376288907 cites W1994213565 @default.
- W4376288907 cites W1994616650 @default.
- W4376288907 cites W2005836623 @default.
- W4376288907 cites W2024375867 @default.
- W4376288907 cites W2034649553 @default.
- W4376288907 cites W2036838083 @default.
- W4376288907 cites W2055334633 @default.
- W4376288907 cites W2067239526 @default.
- W4376288907 cites W2067354736 @default.
- W4376288907 cites W2070030655 @default.
- W4376288907 cites W2072090418 @default.
- W4376288907 cites W2122825543 @default.
- W4376288907 cites W2135294617 @default.
- W4376288907 cites W2150192920 @default.
- W4376288907 cites W2155346693 @default.
- W4376288907 cites W2164452299 @default.
- W4376288907 cites W2531859882 @default.
- W4376288907 cites W2783745237 @default.
- W4376288907 cites W2802151611 @default.
- W4376288907 cites W2950350550 @default.
- W4376288907 cites W2963433607 @default.
- W4376288907 cites W2965795320 @default.
- W4376288907 cites W2978191791 @default.
- W4376288907 cites W3028233350 @default.
- W4376288907 cites W3046122974 @default.
- W4376288907 cites W3098166756 @default.
- W4376288907 cites W3098767358 @default.
- W4376288907 cites W3099181658 @default.
- W4376288907 cites W3101055543 @default.
- W4376288907 cites W3102157992 @default.
- W4376288907 cites W3106513112 @default.
- W4376288907 cites W3161200352 @default.
- W4376288907 cites W3183518399 @default.
- W4376288907 cites W3204146714 @default.
- W4376288907 cites W3208196855 @default.
- W4376288907 cites W4200434021 @default.
- W4376288907 cites W4200577195 @default.
- W4376288907 cites W4226429053 @default.
- W4376288907 cites W4245503300 @default.
- W4376288907 cites W4253577938 @default.
- W4376288907 cites W4287511843 @default.
- W4376288907 cites W4298264214 @default.
- W4376288907 cites W610522045 @default.
- W4376288907 cites W632810616 @default.
- W4376288907 doi "https://doi.org/10.1137/22m1518542" @default.
- W4376288907 hasPublicationYear "2023" @default.
- W4376288907 type Work @default.
- W4376288907 citedByCount "0" @default.
- W4376288907 crossrefType "journal-article" @default.
- W4376288907 hasAuthorship W4376288907A5039605463 @default.
- W4376288907 hasAuthorship W4376288907A5075218826 @default.
- W4376288907 hasBestOaLocation W43762889072 @default.
- W4376288907 hasConcept C126255220 @default.
- W4376288907 hasConcept C132954091 @default.
- W4376288907 hasConcept C134306372 @default.
- W4376288907 hasConcept C135252773 @default.
- W4376288907 hasConcept C140479938 @default.
- W4376288907 hasConcept C154945302 @default.
- W4376288907 hasConcept C162324750 @default.
- W4376288907 hasConcept C206688291 @default.
- W4376288907 hasConcept C207467116 @default.
- W4376288907 hasConcept C2524010 @default.
- W4376288907 hasConcept C2777303404 @default.
- W4376288907 hasConcept C28826006 @default.
- W4376288907 hasConcept C33923547 @default.
- W4376288907 hasConcept C38652104 @default.
- W4376288907 hasConcept C41008148 @default.
- W4376288907 hasConcept C50522688 @default.
- W4376288907 hasConcept C50644808 @default.
- W4376288907 hasConcept C57945734 @default.
- W4376288907 hasConcept C62799726 @default.
- W4376288907 hasConcept C76178495 @default.
- W4376288907 hasConceptScore W4376288907C126255220 @default.
- W4376288907 hasConceptScore W4376288907C132954091 @default.
- W4376288907 hasConceptScore W4376288907C134306372 @default.
- W4376288907 hasConceptScore W4376288907C135252773 @default.
- W4376288907 hasConceptScore W4376288907C140479938 @default.
- W4376288907 hasConceptScore W4376288907C154945302 @default.
- W4376288907 hasConceptScore W4376288907C162324750 @default.
- W4376288907 hasConceptScore W4376288907C206688291 @default.
- W4376288907 hasConceptScore W4376288907C207467116 @default.
- W4376288907 hasConceptScore W4376288907C2524010 @default.
- W4376288907 hasConceptScore W4376288907C2777303404 @default.
- W4376288907 hasConceptScore W4376288907C28826006 @default.
- W4376288907 hasConceptScore W4376288907C33923547 @default.
- W4376288907 hasConceptScore W4376288907C38652104 @default.
- W4376288907 hasConceptScore W4376288907C41008148 @default.
- W4376288907 hasConceptScore W4376288907C50522688 @default.