Matches in SemOpenAlex for { <https://semopenalex.org/work/W4321850195> ?p ?o ?g. }
- W4321850195 endingPage "275" @default.
- W4321850195 startingPage "245" @default.
- W4321850195 abstract "Abstract Numerous intriguing optimization problems arise as a result of the advancement of machine learning. The stochastic first-order method is the predominant choice for those problems due to its high efficiency. However, the negative effects of noisy gradient estimates and high nonlinearity of the loss function result in a slow convergence rate. Second-order algorithms have their typical advantages in dealing with highly nonlinear and ill-conditioning problems. This paper provides a review on recent developments in stochastic variants of quasi-Newton methods, which construct the Hessian approximations using only gradient information. We concentrate on BFGS-based methods in stochastic settings and highlight the algorithmic improvements that enable the algorithm to work in various scenarios. Future research on stochastic quasi-Newton methods should focus on enhancing its applicability, lowering the computational and storage costs, and improving the convergence rate." @default.
- W4321850195 created "2023-02-25" @default.
- W4321850195 creator A5021293751 @default.
- W4321850195 creator A5046469888 @default.
- W4321850195 creator A5091671160 @default.
- W4321850195 date "2023-02-25" @default.
- W4321850195 modified "2023-10-14" @default.
- W4321850195 title "An Overview of Stochastic Quasi-Newton Methods for Large-Scale Machine Learning" @default.
- W4321850195 cites W1970789124 @default.
- W4321850195 cites W1980287119 @default.
- W4321850195 cites W1987083649 @default.
- W4321850195 cites W1991083751 @default.
- W4321850195 cites W1994616650 @default.
- W4321850195 cites W2005136695 @default.
- W4321850195 cites W2006903949 @default.
- W4321850195 cites W2017014514 @default.
- W4321850195 cites W2022772618 @default.
- W4321850195 cites W2024484010 @default.
- W4321850195 cites W2025469203 @default.
- W4321850195 cites W2026393324 @default.
- W4321850195 cites W2038210983 @default.
- W4321850195 cites W2042173174 @default.
- W4321850195 cites W2045744861 @default.
- W4321850195 cites W2051434435 @default.
- W4321850195 cites W2051669046 @default.
- W4321850195 cites W2053964895 @default.
- W4321850195 cites W2061570747 @default.
- W4321850195 cites W2064217481 @default.
- W4321850195 cites W2078394884 @default.
- W4321850195 cites W2078409719 @default.
- W4321850195 cites W2095211439 @default.
- W4321850195 cites W2112796928 @default.
- W4321850195 cites W2130984546 @default.
- W4321850195 cites W2137825550 @default.
- W4321850195 cites W2295492468 @default.
- W4321850195 cites W2316564661 @default.
- W4321850195 cites W2586740245 @default.
- W4321850195 cites W2605483263 @default.
- W4321850195 cites W2727020975 @default.
- W4321850195 cites W2734739919 @default.
- W4321850195 cites W2763081248 @default.
- W4321850195 cites W2797791799 @default.
- W4321850195 cites W2804009132 @default.
- W4321850195 cites W2804140211 @default.
- W4321850195 cites W2900789157 @default.
- W4321850195 cites W2912848192 @default.
- W4321850195 cites W2943853279 @default.
- W4321850195 cites W2963060476 @default.
- W4321850195 cites W2963242954 @default.
- W4321850195 cites W2963307318 @default.
- W4321850195 cites W2963312217 @default.
- W4321850195 cites W2963397933 @default.
- W4321850195 cites W2963433607 @default.
- W4321850195 cites W2963575360 @default.
- W4321850195 cites W2963775310 @default.
- W4321850195 cites W2963941964 @default.
- W4321850195 cites W2964051671 @default.
- W4321850195 cites W2964303576 @default.
- W4321850195 cites W2964312150 @default.
- W4321850195 cites W2970227300 @default.
- W4321850195 cites W2971697083 @default.
- W4321850195 cites W2980908801 @default.
- W4321850195 cites W2997241048 @default.
- W4321850195 cites W2999729425 @default.
- W4321850195 cites W3005768517 @default.
- W4321850195 cites W3016907649 @default.
- W4321850195 cites W3030916542 @default.
- W4321850195 cites W3088745370 @default.
- W4321850195 cites W3091424096 @default.
- W4321850195 cites W3096562082 @default.
- W4321850195 cites W3127411449 @default.
- W4321850195 cites W3128577503 @default.
- W4321850195 cites W3131338793 @default.
- W4321850195 cites W3138544340 @default.
- W4321850195 cites W3152845623 @default.
- W4321850195 cites W3169062464 @default.
- W4321850195 cites W3185298382 @default.
- W4321850195 cites W3197425639 @default.
- W4321850195 cites W3201675503 @default.
- W4321850195 cites W3206876740 @default.
- W4321850195 cites W4200599756 @default.
- W4321850195 cites W4225873238 @default.
- W4321850195 cites W4230884253 @default.
- W4321850195 cites W4231147569 @default.
- W4321850195 doi "https://doi.org/10.1007/s40305-023-00453-9" @default.
- W4321850195 hasPublicationYear "2023" @default.
- W4321850195 type Work @default.
- W4321850195 citedByCount "0" @default.
- W4321850195 crossrefType "journal-article" @default.
- W4321850195 hasAuthorship W4321850195A5021293751 @default.
- W4321850195 hasAuthorship W4321850195A5046469888 @default.
- W4321850195 hasAuthorship W4321850195A5091671160 @default.
- W4321850195 hasBestOaLocation W43218501951 @default.
- W4321850195 hasConcept C11413529 @default.
- W4321850195 hasConcept C114954040 @default.
- W4321850195 hasConcept C120665830 @default.
- W4321850195 hasConcept C121332964 @default.
- W4321850195 hasConcept C126255220 @default.