Matches in SemOpenAlex for { <https://semopenalex.org/work/W3165046413> ?p ?o ?g. }
- W3165046413 abstract "This paper studies the theoretical underpinnings of machine learning of ergodic Ito diffusions. The objective is to understand the convergence properties of the invariant statistics when the underlying system of stochastic differential equations (SDEs) is empirically estimated with a supervised regression framework. Using the perturbation theory of ergodic Markov chains and the linear response theory, we deduce a linear dependence of the errors of one-point and two-point invariant statistics on the error in the learning of the drift and diffusion coefficients. More importantly, our study shows that the usual $L^2$-norm characterization of the learning generalization error is insufficient for achieving this linear dependence result. We find that sufficient conditions for such a linear dependence result are through learning algorithms that produce a uniformly Lipschitz and consistent estimator in the hypothesis space that retains certain characteristics of the drift coefficients, such as the usual linear growth condition that guarantees the existence of solutions of the underlying SDEs. We examine these conditions on two well-understood learning algorithms: the kernel-based spectral regression method and the shallow random neural networks with the ReLU activation function." @default.
- W3165046413 created "2021-06-07" @default.
- W3165046413 creator A5034663047 @default.
- W3165046413 creator A5062986633 @default.
- W3165046413 creator A5064323494 @default.
- W3165046413 date "2021-05-21" @default.
- W3165046413 modified "2023-09-27" @default.
- W3165046413 title "Error Bounds of the Invariant Statistics in Machine Learning of Ergodic It^o Diffusions" @default.
- W3165046413 cites W1486396968 @default.
- W3165046413 cites W1575104486 @default.
- W3165046413 cites W1604264128 @default.
- W3165046413 cites W1698155719 @default.
- W3165046413 cites W1703488510 @default.
- W3165046413 cites W1909010623 @default.
- W3165046413 cites W1968436459 @default.
- W3165046413 cites W196973002 @default.
- W3165046413 cites W2002276939 @default.
- W3165046413 cites W2012501405 @default.
- W3165046413 cites W2021270935 @default.
- W3165046413 cites W2021972235 @default.
- W3165046413 cites W2036331698 @default.
- W3165046413 cites W2047278710 @default.
- W3165046413 cites W2059910636 @default.
- W3165046413 cites W2060182299 @default.
- W3165046413 cites W2069264695 @default.
- W3165046413 cites W2071342641 @default.
- W3165046413 cites W2071889960 @default.
- W3165046413 cites W2077180490 @default.
- W3165046413 cites W2083496527 @default.
- W3165046413 cites W2099973661 @default.
- W3165046413 cites W2103757834 @default.
- W3165046413 cites W2104049095 @default.
- W3165046413 cites W2118706537 @default.
- W3165046413 cites W2122771530 @default.
- W3165046413 cites W2125875378 @default.
- W3165046413 cites W2137606648 @default.
- W3165046413 cites W2170316986 @default.
- W3165046413 cites W2176027706 @default.
- W3165046413 cites W2234596001 @default.
- W3165046413 cites W2323824333 @default.
- W3165046413 cites W2583612756 @default.
- W3165046413 cites W2607078470 @default.
- W3165046413 cites W2782714865 @default.
- W3165046413 cites W284160648 @default.
- W3165046413 cites W2962851953 @default.
- W3165046413 cites W2963627589 @default.
- W3165046413 cites W2963687408 @default.
- W3165046413 cites W2976645955 @default.
- W3165046413 cites W3006049408 @default.
- W3165046413 cites W3016578580 @default.
- W3165046413 cites W3029144177 @default.
- W3165046413 cites W3041887065 @default.
- W3165046413 cites W3042253907 @default.
- W3165046413 cites W3085553537 @default.
- W3165046413 cites W3101784309 @default.
- W3165046413 cites W3102026477 @default.
- W3165046413 cites W3106310231 @default.
- W3165046413 cites W3115821566 @default.
- W3165046413 cites W3117735472 @default.
- W3165046413 cites W3210853058 @default.
- W3165046413 hasPublicationYear "2021" @default.
- W3165046413 type Work @default.
- W3165046413 sameAs 3165046413 @default.
- W3165046413 citedByCount "1" @default.
- W3165046413 countsByYear W31650464132021 @default.
- W3165046413 crossrefType "posted-content" @default.
- W3165046413 hasAuthorship W3165046413A5034663047 @default.
- W3165046413 hasAuthorship W3165046413A5062986633 @default.
- W3165046413 hasAuthorship W3165046413A5064323494 @default.
- W3165046413 hasConcept C105795698 @default.
- W3165046413 hasConcept C122044880 @default.
- W3165046413 hasConcept C134306372 @default.
- W3165046413 hasConcept C185429906 @default.
- W3165046413 hasConcept C190470478 @default.
- W3165046413 hasConcept C22324862 @default.
- W3165046413 hasConcept C28826006 @default.
- W3165046413 hasConcept C33923547 @default.
- W3165046413 hasConcept C37914503 @default.
- W3165046413 hasConcept C48921125 @default.
- W3165046413 hasConcept C51955184 @default.
- W3165046413 hasConceptScore W3165046413C105795698 @default.
- W3165046413 hasConceptScore W3165046413C122044880 @default.
- W3165046413 hasConceptScore W3165046413C134306372 @default.
- W3165046413 hasConceptScore W3165046413C185429906 @default.
- W3165046413 hasConceptScore W3165046413C190470478 @default.
- W3165046413 hasConceptScore W3165046413C22324862 @default.
- W3165046413 hasConceptScore W3165046413C28826006 @default.
- W3165046413 hasConceptScore W3165046413C33923547 @default.
- W3165046413 hasConceptScore W3165046413C37914503 @default.
- W3165046413 hasConceptScore W3165046413C48921125 @default.
- W3165046413 hasConceptScore W3165046413C51955184 @default.
- W3165046413 hasLocation W31650464131 @default.
- W3165046413 hasOpenAccess W3165046413 @default.
- W3165046413 hasPrimaryLocation W31650464131 @default.
- W3165046413 hasRelatedWork W197246843 @default.
- W3165046413 hasRelatedWork W2165471239 @default.
- W3165046413 hasRelatedWork W2185422628 @default.
- W3165046413 hasRelatedWork W2195777266 @default.
- W3165046413 hasRelatedWork W2208753692 @default.
- W3165046413 hasRelatedWork W2550249781 @default.