Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published May 24, 2022 | Submitted
Report Open

Convergence Rates for Learning Linear Operators from Noisy Data

Abstract

We study the Bayesian inverse problem of learning a linear operator on a Hilbert space from its noisy pointwise evaluations on random input data. Our framework assumes that this target operator is self-adjoint and diagonal in a basis shared with the Gaussian prior and noise covariance operators arising from the imposed statistical model and is able to handle target operators that are compact, bounded, or even unbounded. We establish posterior contraction rates with respect to a family of Bochner norms as the number of data tend to infinity and derive related lower bounds on the estimation error. In the large data limit, we also provide asymptotic convergence rates of suitably defined excess risk and generalization gap functionals associated with the posterior mean point estimator. In doing so, we connect the posterior consistency results to nonparametric learning theory. Furthermore, these convergence rates highlight and quantify the difficulty of learning unbounded linear operators in comparison with the learning of bounded or compact ones. Numerical experiments confirm the theory and demonstrate that similar conclusions may be expected in more general problem settings.

Additional Information

The authors thank Kamyar Azizzadenesheli and Joel A. Tropp for helpful discussions about statistical learning. The computations presented in this paper were conducted on the Resnick High Performance Computing Center, a facility supported by the Resnick Sustainability Institute at the California Institute of Technology. MVdH is supported by the Simons Foundation under the MATH + X program, U.S. Department of Energy, Office of Basic Energy Sciences, Chemical Sciences, Geosciences, and Biosciences Division under grant number DE-SC0020345, the National Science Foundation (NSF) under grant DMS-1815143, and the corporate members of the Geo-Mathematical Imaging Group at Rice University. NHN is supported by the NSF Graduate Research Fellowship Program under grant DGE-1745301. AMS is supported by NSF (grant DMS-1818977). NBK, NHN, and AMS are supported by NSF (grant AGS-1835860) and ONR (grant N00014-19-1-2408).

Attached Files

Submitted - 2108.12515.pdf

Files

2108.12515.pdf
Files (972.9 kB)
Name Size Download all
md5:b83814161a9deb6b26fbf670e17114ea
972.9 kB Preview Download

Additional details

Created:
August 20, 2023
Modified:
October 24, 2023