Matches in SemOpenAlex for { <https://semopenalex.org/work/W3046391292> ?p ?o ?g. }
- W3046391292 abstract "In this paper, we establish the almost sure convergence of two-timescale stochastic gradient descent algorithms in continuous time under general noise and stability conditions, extending well known results in discrete time. We analyse algorithms with additive noise and those with non-additive noise. In the non-additive case, our analysis is carried out under the assumption that the noise is a continuous-time Markov process, controlled by the algorithm states. The algorithms we consider can be applied to a broad class of bilevel optimisation problems. We study one such problem in detail, namely, the problem of joint online parameter estimation and optimal sensor placement for a partially observed diffusion process. We demonstrate how this can be formulated as a bilevel optimisation problem, and propose a solution in the form of a continuous-time, two-timescale, stochastic gradient descent algorithm. Furthermore, under suitable conditions on the latent signal, the filter, and the filter derivatives, we establish almost sure convergence of the online parameter estimates and optimal sensor placements to the stationary points of the asymptotic log-likelihood and asymptotic filter covariance, respectively. We also provide numerical examples, illustrating the application of the proposed methodology to a partially observed Beneš equation, and a partially observed stochastic advection-diffusion equation." @default.
- W3046391292 created "2020-08-07" @default.
- W3046391292 creator A5031347000 @default.
- W3046391292 creator A5060221398 @default.
- W3046391292 date "2023-05-01" @default.
- W3046391292 modified "2023-10-14" @default.
- W3046391292 title "Two-timescale stochastic gradient descent in continuous time with applications to joint online parameter estimation and optimal sensor placement" @default.
- W3046391292 cites W1223110754 @default.
- W3046391292 cites W1491706803 @default.
- W3046391292 cites W1498711961 @default.
- W3046391292 cites W1568229137 @default.
- W3046391292 cites W1568531505 @default.
- W3046391292 cites W1573874356 @default.
- W3046391292 cites W1596696791 @default.
- W3046391292 cites W1967049706 @default.
- W3046391292 cites W1971942712 @default.
- W3046391292 cites W1973162763 @default.
- W3046391292 cites W1973457547 @default.
- W3046391292 cites W1974006687 @default.
- W3046391292 cites W1985142115 @default.
- W3046391292 cites W1985291828 @default.
- W3046391292 cites W1993777584 @default.
- W3046391292 cites W2007854530 @default.
- W3046391292 cites W2009303086 @default.
- W3046391292 cites W2011866684 @default.
- W3046391292 cites W2015836240 @default.
- W3046391292 cites W2016005401 @default.
- W3046391292 cites W2020782783 @default.
- W3046391292 cites W2022327893 @default.
- W3046391292 cites W2044450877 @default.
- W3046391292 cites W2044641957 @default.
- W3046391292 cites W2047078272 @default.
- W3046391292 cites W2050447955 @default.
- W3046391292 cites W2059633697 @default.
- W3046391292 cites W2071983464 @default.
- W3046391292 cites W2073283839 @default.
- W3046391292 cites W2077991515 @default.
- W3046391292 cites W2078618768 @default.
- W3046391292 cites W2079321251 @default.
- W3046391292 cites W2082261506 @default.
- W3046391292 cites W2082794610 @default.
- W3046391292 cites W2083402998 @default.
- W3046391292 cites W2094364653 @default.
- W3046391292 cites W2113373687 @default.
- W3046391292 cites W2124202837 @default.
- W3046391292 cites W2124975090 @default.
- W3046391292 cites W2125812768 @default.
- W3046391292 cites W2127726220 @default.
- W3046391292 cites W2139992903 @default.
- W3046391292 cites W2152767074 @default.
- W3046391292 cites W2224385813 @default.
- W3046391292 cites W2235056388 @default.
- W3046391292 cites W2321597899 @default.
- W3046391292 cites W2550039210 @default.
- W3046391292 cites W2625792078 @default.
- W3046391292 cites W2687264408 @default.
- W3046391292 cites W2783033216 @default.
- W3046391292 cites W2890735266 @default.
- W3046391292 cites W2963313444 @default.
- W3046391292 cites W2963469405 @default.
- W3046391292 cites W2964163851 @default.
- W3046391292 cites W2996964934 @default.
- W3046391292 cites W3033360065 @default.
- W3046391292 cites W3087503551 @default.
- W3046391292 cites W3097149416 @default.
- W3046391292 cites W3102232514 @default.
- W3046391292 cites W3106072647 @default.
- W3046391292 cites W3116168490 @default.
- W3046391292 cites W3194113352 @default.
- W3046391292 cites W3294551 @default.
- W3046391292 cites W4211127940 @default.
- W3046391292 cites W4238063566 @default.
- W3046391292 cites W4241599172 @default.
- W3046391292 cites W4243772471 @default.
- W3046391292 cites W4243794326 @default.
- W3046391292 cites W4245280614 @default.
- W3046391292 cites W4250389103 @default.
- W3046391292 cites W4253242510 @default.
- W3046391292 cites W59502071 @default.
- W3046391292 cites W2032173367 @default.
- W3046391292 cites W2097558742 @default.
- W3046391292 doi "https://doi.org/10.3150/22-bej1493" @default.
- W3046391292 hasPublicationYear "2023" @default.
- W3046391292 type Work @default.
- W3046391292 sameAs 3046391292 @default.
- W3046391292 citedByCount "1" @default.
- W3046391292 countsByYear W30463912922023 @default.
- W3046391292 crossrefType "journal-article" @default.
- W3046391292 hasAuthorship W3046391292A5031347000 @default.
- W3046391292 hasAuthorship W3046391292A5060221398 @default.
- W3046391292 hasBestOaLocation W30463912922 @default.
- W3046391292 hasConcept C105795698 @default.
- W3046391292 hasConcept C106131492 @default.
- W3046391292 hasConcept C11413529 @default.
- W3046391292 hasConcept C115961682 @default.
- W3046391292 hasConcept C119857082 @default.
- W3046391292 hasConcept C126255220 @default.
- W3046391292 hasConcept C153258448 @default.
- W3046391292 hasConcept C154945302 @default.
- W3046391292 hasConcept C162324750 @default.