Deep neural network expression of posterior expectations in Bayesian PDE inversion
For Bayesian inverse problems with input-to-response maps given by well-posed partial differential equations and subject to uncertain parametric or function space input, we establish (under rather weak conditions on the ‘forward’, input-to-response maps) the parametric holomorphy of the data-to-QoI...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
3 December 2020
|
| In: |
Inverse problems
Year: 2020, Volume: 36, Issue: 12 |
| ISSN: | 1361-6420 |
| DOI: | 10.1088/1361-6420/abaf64 |
| Online Access: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1088/1361-6420/abaf64 Verlag, lizenzpflichtig, Volltext: https://iopscience.iop.org/article/10.1088/1361-6420/abaf64 
|
| Author Notes: | Lukas Herrmann, Christoph Schwab and Jakob Zech |
| Summary: | For Bayesian inverse problems with input-to-response maps given by well-posed partial differential equations and subject to uncertain parametric or function space input, we establish (under rather weak conditions on the ‘forward’, input-to-response maps) the parametric holomorphy of the data-to-QoI map relating observation data δ to the Bayesian estimate for an unknown quantity of interest (QoI). We prove exponential expression rate bounds for this data-to-QoI map by deep neural networks with rectified linear unit activation function, which are uniform with respect to the data δ taking values in a compact subset of . Similar convergence rates are verified for polynomial and rational approximations of the data-to-QoI map. We discuss the extension to other activation functions, and to mere Lipschitz continuity of the data-to-QoI map. |
|---|---|
| Item Description: | Gesehen am 14.01.2021 |
| Physical Description: | Online Resource |
| ISSN: | 1361-6420 |
| DOI: | 10.1088/1361-6420/abaf64 |