Learning with known operators reduces maximum error bounds
نویسندگان
چکیده
منابع مشابه
Learning regression models with guaranteed error bounds
The combination of a symbolic regression model with a residual Gaussian Process is proposed for providing an interpretable model with improved accuracy. While the learned symbolic model is highly interpretable the residual model usually is not. However, by limiting the output of the residual model to a defined range a worst-case guarantee can be given in the sense that the maximal deviation fro...
متن کاملBuilding Data Synopses Within a Known Maximum Error Bound
The constructions of Haar wavelet synopses for large data sets have proven to be useful tools for data approximation. Recently, research on constructing wavelet synopses with a guaranteed maximum error has gained attention. Two relevant problems have been proposed: One is the size bounded problem that requires the construction of a synopsis of a given size to minimize the maximum error. Another...
متن کاملError bounds in approximating n-time differentiable functions of self-adjoint operators in Hilbert spaces via a Taylor's type expansion
On utilizing the spectral representation of selfadjoint operators in Hilbert spaces, some error bounds in approximating $n$-time differentiable functions of selfadjoint operators in Hilbert Spaces via a Taylor's type expansion are given.
متن کاملBounds on the Maximum Bayes Error Given Moments
We show how to compute lower bounds for the maximum possible Bayes error if the class-conditional distributions must satisfy moment constraints. Our approach makes use of Curto and Fialkow’s solutions for the truncated moment problem. We also give an upper bound that follows from related work by Lanckreit et al., Bertsimas and Popescu, and Marshall and Olkin. Index Terms Bayes error, maximum en...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Nature Machine Intelligence
سال: 2019
ISSN: 2522-5839
DOI: 10.1038/s42256-019-0077-5