Matches in SemOpenAlex for { <https://semopenalex.org/work/W3028316595> ?p ?o ?g. }
- W3028316595 abstract "Well known to the machine learning community, the random feature model, originally introduced by Rahimi and Recht in 2008, is a parametric approximation to kernel interpolation or regression methods. It is typically used to approximate functions mapping a finite-dimensional input space to the real line. In this paper, we instead propose a methodology for use of the random feature model as a data-driven surrogate for operators that map an input Banach space to an output Banach space. Although the methodology is quite general, we consider operators defined by partial differential equations (PDEs); here, the inputs and outputs are themselves functions, with the input parameters being functions required to specify the problem, such as initial data or coefficients, and the outputs being solutions of the problem. Upon discretization, the model inherits several desirable attributes from this infinite-dimensional, function space viewpoint, including mesh-invariant approximation error with respect to the true PDE solution map and the capability to be trained at one mesh resolution and then deployed at different mesh resolutions. We view the random feature model as a non-intrusive data-driven emulator, provide a mathematical framework for its interpretation, and demonstrate its ability to efficiently and accurately approximate the nonlinear parameter-to-solution maps of two prototypical PDEs arising in physical science and engineering applications: viscous Burgers' equation and a variable coefficient elliptic equation." @default.
- W3028316595 created "2020-05-29" @default.
- W3028316595 creator A5032114852 @default.
- W3028316595 creator A5089738825 @default.
- W3028316595 date "2020-05-20" @default.
- W3028316595 modified "2023-09-26" @default.
- W3028316595 title "The Random Feature Model for Input-Output Maps between Banach Spaces" @default.
- W3028316595 cites W1486164486 @default.
- W3028316595 cites W1534416612 @default.
- W3028316595 cites W1544131626 @default.
- W3028316595 cites W1554944419 @default.
- W3028316595 cites W1558122728 @default.
- W3028316595 cites W1565176583 @default.
- W3028316595 cites W1600371943 @default.
- W3028316595 cites W1746819321 @default.
- W3028316595 cites W1793403863 @default.
- W3028316595 cites W1866311589 @default.
- W3028316595 cites W1965597870 @default.
- W3028316595 cites W1972005403 @default.
- W3028316595 cites W1976068300 @default.
- W3028316595 cites W1981328984 @default.
- W3028316595 cites W1986280275 @default.
- W3028316595 cites W2012501405 @default.
- W3028316595 cites W2020854958 @default.
- W3028316595 cites W2027319740 @default.
- W3028316595 cites W2047278710 @default.
- W3028316595 cites W2047591100 @default.
- W3028316595 cites W2073469810 @default.
- W3028316595 cites W2101948461 @default.
- W3028316595 cites W2115003579 @default.
- W3028316595 cites W2117188967 @default.
- W3028316595 cites W2123395972 @default.
- W3028316595 cites W2133027741 @default.
- W3028316595 cites W2139923370 @default.
- W3028316595 cites W2144902422 @default.
- W3028316595 cites W2146552914 @default.
- W3028316595 cites W2152657433 @default.
- W3028316595 cites W2154010977 @default.
- W3028316595 cites W2154087390 @default.
- W3028316595 cites W2165867509 @default.
- W3028316595 cites W2166116275 @default.
- W3028316595 cites W2234882433 @default.
- W3028316595 cites W2236957706 @default.
- W3028316595 cites W2489279134 @default.
- W3028316595 cites W2532798880 @default.
- W3028316595 cites W2582800953 @default.
- W3028316595 cites W2600297185 @default.
- W3028316595 cites W2749028154 @default.
- W3028316595 cites W2760972773 @default.
- W3028316595 cites W2765872171 @default.
- W3028316595 cites W2766298346 @default.
- W3028316595 cites W2784733489 @default.
- W3028316595 cites W2786232134 @default.
- W3028316595 cites W2809090039 @default.
- W3028316595 cites W2811395263 @default.
- W3028316595 cites W2883486956 @default.
- W3028316595 cites W2891039272 @default.
- W3028316595 cites W2897491795 @default.
- W3028316595 cites W2899283552 @default.
- W3028316595 cites W2930017973 @default.
- W3028316595 cites W2933916181 @default.
- W3028316595 cites W2944808962 @default.
- W3028316595 cites W2946866513 @default.
- W3028316595 cites W2948801778 @default.
- W3028316595 cites W2950776240 @default.
- W3028316595 cites W2951756126 @default.
- W3028316595 cites W2963515392 @default.
- W3028316595 cites W2963518130 @default.
- W3028316595 cites W2963709899 @default.
- W3028316595 cites W2963798430 @default.
- W3028316595 cites W2968880761 @default.
- W3028316595 cites W2970332347 @default.
- W3028316595 cites W2972663523 @default.
- W3028316595 cites W2974916071 @default.
- W3028316595 cites W2980396542 @default.
- W3028316595 cites W2986795381 @default.
- W3028316595 cites W2995857625 @default.
- W3028316595 cites W2998149507 @default.
- W3028316595 cites W3004630109 @default.
- W3028316595 cites W3005100040 @default.
- W3028316595 cites W3010501116 @default.
- W3028316595 cites W3020191331 @default.
- W3028316595 cites W3021722416 @default.
- W3028316595 cites W3021748939 @default.
- W3028316595 cites W3035079212 @default.
- W3028316595 cites W3080853598 @default.
- W3028316595 cites W3087889215 @default.
- W3028316595 cites W3092923133 @default.
- W3028316595 cites W3098011980 @default.
- W3028316595 cites W3103322710 @default.
- W3028316595 cites W3104266598 @default.
- W3028316595 cites W3108655421 @default.
- W3028316595 cites W3112068713 @default.
- W3028316595 cites W3124293288 @default.
- W3028316595 cites W3126538074 @default.
- W3028316595 cites W3158351273 @default.
- W3028316595 cites W626074782 @default.
- W3028316595 hasPublicationYear "2020" @default.
- W3028316595 type Work @default.
- W3028316595 sameAs 3028316595 @default.