paper-with-me

홈 › Papers

Deep generative demixing: Recovering Lipschitz signals from noisy subgaussian mixtures

2020-10-13 · Aaron Berk

Generative neural networks (GNNs) have gained renown for efficaciously capturing intrinsic low-dimensional structure in natural images. Here, we investigate the subgaussian demixing problem for two Lipschitz signals, with GNN demixing as a special case. In demixing, one seeks identification of two signals given their sum and prior structural information. Here, we assume each signal lies in the range of a Lipschitz function, which includes many popular GNNs as a special case. We prove a sample complexity bound for nearly optimal recovery error that extends a recent result of Bora, et al. (2017) from the compressed sensing setting with gaussian matrices to demixing with subgaussian ones. Under a linear signal model in which the signals lie in convex sets, McCoy & Tropp (2014) have characterized the sample complexity for identification under subgaussian mixing. In the present setting, the signal structure need not be convex. For example, our result applies to a domain that is a non-convex union of convex cones. We support the efficacy of this demixing model with numerical simulations using trained GNNs, suggesting an algorithm that would be an interesting object of further theoretical study.

📄 PDF Abstract BibTeX arXiv:2010.06652

Code (0)

등록된 구현이 없습니다.

Tasks

compressed sensing

Similar Papers 제목 키워드 기반

Fast Algorithms for Demixing Sparse Signals from Nonlinear Observations

2016-08-03 · Mohammadreza Soltani, Chinmay Hegde

We study the problem of demixing a pair of sparse signals from noisy, nonlinear observations of their superposition. Mathematically, we consider a nonlinear signal observation model, $y_i = g(a_i^Tx) + e_i, \ i=1,\ldots,…

Astronomy

Nonconvex Demixing From Bilinear Measurements

2018-09-18 · Jialin Dong, Yuanming Shi

We consider the problem of demixing a sequence of source signals from the sum of noisy bilinear measurements. It is a generalized mathematical model for blind demixing with blind deconvolution, which is prevalent across …

Dictionary Learning

LEARNING GENERATIVE MODELS FOR DEMIXING OF STRUCTURED SIGNALS FROM THEIR SUPERPOSITION USING GANS

2019-05-01 · ICLR 2019 5 · Mohammadreza Soltani, Swayambhoo Jain, Abhinav V. Sambasivan

Recently, Generative Adversarial Networks (GANs) have emerged as a popular alternative for modeling complex high dimensional distributions. Most of the existing works implicitly assume that the clean samples from the tar…

Compressive SensingDenoising

Learning Generative Models of Structured Signals from Their Superposition Using GANs with Application to Denoising and Demixing

2019-02-12 · Mohammadreza Soltani, Swayambhoo Jain, Abhinav Sambasivan

Recently, Generative Adversarial Networks (GANs) have emerged as a popular alternative for modeling complex high dimensional distributions. Most of the existing works implicitly assume that the clean samples from the tar…

Compressive SensingDenoising

Unsupervised Demixing of Structured Signals from Their Superposition Using GANs

2019-03-27 · ICLR Workshop DeepGenStruct 2019 · Mohammadreza Soltani, Swayambhoo Jain, Abhinav Sambasivan

Recently, Generative Adversarial Networks (GANs) have emerged as a popular alternative for modeling complex high dimensional distributions. Most of the existing works implicitly assume that the clean samples from the tar…