Global Guarantees for Enforcing Deep Generative Priors by Empirical Risk

DOI10.1109/TIT.2019.2935447zbMath1433.94024arXiv1705.07576OpenAlexW2967360854MaRDI QIDQ5211608

Vladislav Voroninski, Paul E. Hand

Publication date: 28 January 2020

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1705.07576

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Related Items (8)

A provably convergent scheme for compressive sensing under random generative priors ⋮ Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior ⋮ Sharp global convergence guarantees for iterative nonconvex optimization with random data ⋮ Compressive phase retrieval: Optimal sample complexity with deep generative priors ⋮ Regularising inverse problems with generative machine learning models ⋮ Consistent approximations in composite optimization ⋮ Applied harmonic analysis and data processing. Abstracts from the workshop held March 25--31, 2018 ⋮ Matrix inference and estimation in multi-layer models*

This page was built for publication: Global Guarantees for Enforcing Deep Generative Priors by Empirical Risk