Learned SVD: solving inverse problems via hybrid autoencoding
Our world is full of physics-driven data where effective mappings between data manifolds are desired. There is an increasing demand for understanding combined model-driven and data-driven learning methods. We propose a nonlinear, learned singular value decomposition (L-SVD), which combines autoencoders that simultaneously learn and connect latent codes for desired signals and given measurements. Classical solution methods for inverse problems are based on regularisation techniques via SVD and variational methods. An open topic in deep learning for inverse problems is how to achieve model reduction via data dimensionality reduction to obtain a regularised inversion. We investigate this topic and provide a promising direction for solving inverse problems in cases where the underlying physics are not fully understood or have very complex behaviour. We show that the building blocks of learned inversion maps can be obtained automatically, with improved performance upon classical methods and better interpretability than black-box methods.
READ FULL TEXT