no code implementations • 9 Dec 2019 • Francois Lanusse, Peter Melchior, Fred Moolekamp
We present a Bayesian machine learning architecture that combines a physically motivated parametrization and an analytic error model for the likelihood with a deep generative model providing a powerful data-driven prior for complex signals.
4 code implementations • 27 Feb 2018 • Peter Melchior, Fred Moolekamp, Maximilian Jerdee, Robert Armstrong, Ai-Lei Sun, James Bosch, Robert Lupton
We present the source separation framework SCARLET for multi-band images, which is based on a generalization of the Non-negative Matrix Factorization to alternative and several simultaneous constraints.
Instrumentation and Methods for Astrophysics
3 code implementations • 30 Aug 2017 • Fred Moolekamp, Peter Melchior
We introduce a generalization of the linearized Alternating Direction Method of Multipliers to optimize a real-valued function $f$ of multiple arguments with potentially multiple constraints $g_\circ$ on each of them.