Timezone: »
Many problems in statistics and machine learning require the reconstruction of a rank-one signal matrix from noisy data. Enforcing additional prior information on the rank-one component is often key to guaranteeing good recovery performance. One such prior on the low-rank component is sparsity, giving rise to the sparse principal component analysis problem. Unfortunately, there is strong evidence that this problem suffers from a computational-to-statistical gap, which may be fundamental. In this work, we study an alternative prior where the low-rank component is in the range of a trained generative network. We provide a non-asymptotic analysis with optimal sample complexity, up to logarithmic factors, for rank-one matrix recovery under an expansive-Gaussian network prior. Specifically, we establish a favorable global optimization landscape for a nonlinear least squares objective, provided the number of samples is on the order of the dimensionality of the input to the generative model. This result suggests that generative priors have no computational-to-statistical gap for structured rank-one matrix recovery in the finite data, nonasymptotic regime. We present this analysis in the case of both the Wishart and Wigner spiked matrix models.
Author Information
Jorio Cocola (Northeastern University)
Paul Hand (Northeastern University)
Vlad Voroninski (Helm.ai)
More from the Same Authors
-
2022 Poster: Signal Recovery with Non-Expansive Generative Network Priors »
Jorio Cocola -
2021 Workshop: Workshop on Deep Learning and Inverse Problems »
Reinhard Heckel · Paul Hand · Rebecca Willett · christopher metzler · Mahdi Soltanolkotabi -
2021 Poster: Score-based Generative Neural Networks for Large-Scale Optimal Transport »
Grady Daniels · Tyler Maunu · Paul Hand -
2020 : Opening Remarks »
Reinhard Heckel · Paul Hand · Soheil Feizi · Lenka Zdeborová · Richard Baraniuk -
2020 Workshop: Workshop on Deep Learning and Inverse Problems »
Reinhard Heckel · Paul Hand · Richard Baraniuk · Lenka Zdeborová · Soheil Feizi -
2020 : Newcomer presentation »
Reinhard Heckel · Paul Hand -
2019 : Opening Remarks »
Reinhard Heckel · Paul Hand · Alex Dimakis · Joan Bruna · Deanna Needell · Richard Baraniuk -
2019 Workshop: Solving inverse problems with deep networks: New architectures, theoretical foundations, and applications »
Reinhard Heckel · Paul Hand · Richard Baraniuk · Joan Bruna · Alex Dimakis · Deanna Needell -
2019 Poster: Global Guarantees for Blind Demodulation with Generative Priors »
Paul Hand · Babhru Joshi -
2018 Poster: A convex program for bilinear inversion of sparse vectors »
Alireza Aghasi · Ali Ahmed · Paul Hand · Babhru Joshi -
2018 Poster: Blind Deconvolutional Phase Retrieval via Convex Programming »
Ali Ahmed · Alireza Aghasi · Paul Hand -
2018 Spotlight: Blind Deconvolutional Phase Retrieval via Convex Programming »
Ali Ahmed · Alireza Aghasi · Paul Hand -
2018 Poster: Phase Retrieval Under a Generative Prior »
Paul Hand · Oscar Leong · Vlad Voroninski -
2018 Oral: Phase Retrieval Under a Generative Prior »
Paul Hand · Oscar Leong · Vlad Voroninski