Andreas M. Tillmann — accepted AI-conference papers

2021

A Parallel Algorithm for Phase Retrieval with Dictionary Learning

Tianyi Liu, Andreas M. Tillmann, Yang Yang, Yonina C. Eldar, Marius Pesavento

ICASSP 2021accepted

We propose a new formulation for the joint phase retrieval and dictionary learning problem with a reduced number of regularization parameters to be tuned. A parallel algorithm based on the block successive convex approximation framework is developed for the proposed formulation. The performance of t…

Cited by 5 Source ↗Scholar ↗

2016

Dictionary learning from phaseless measurements

Andreas M. Tillmann, Yonina C. Eldar, Julien Mairal

ICASSP 2016accepted

We propose a new algorithm to learn a dictionary along with sparse representations from signal measurements without phase. Specifically, we consider the task of reconstructing a two-dimensional image from squared-magnitude measurements of a complex-valued linear transformation of the original image.…

Cited by 6 Source ↗Scholar ↗