Log In Sign Up

Robust One-Bit Recovery via ReLU Generative Networks: Improved Statistical Rates and Global Landscape Analysis

by   Shuang Qiu, et al.

We study the robust one-bit compressed sensing problem whose goal is to design an algorithm that faithfully recovers any sparse target vector θ_0∈R^d uniformly m quantized noisy measurements. Under the assumption that the measurements are sub-Gaussian random vectors, to recover any k-sparse θ_0 (k≪ d) uniformly up to an error ε with high probability, the best known computationally tractable algorithm requires m≥Õ(klog d/ε^4) measurements. In this paper, we consider a new framework for the one-bit sensing problem where the sparsity is implicitly enforced via mapping a low dimensional representation x_0 ∈R^k through a known n-layer ReLU generative network G:R^k→R^d. Such a framework poses low-dimensional priors on θ_0 without a known basis. We propose to recover the target G(x_0) via an unconstrained empirical risk minimization (ERM) problem under a much weaker sub-exponential measurement assumption. For such a problem, we establish a joint statistical and computational analysis. In particular, we prove that the ERM estimator in this new framework achieves an improved statistical rate of m=Õ(kn log d /ε^2) recovering any G(x_0) uniformly up to an error ε. Moreover, from the lens of computation, despite non-convexity, we prove that the objective of our ERM problem has no spurious stationary point, that is, any stationary point are equally good for recovering the true target up to scaling with a certain accuracy. Furthermore, our analysis also shed lights on the possibility of inverting a deep generative model under partial and quantized measurements, complementing the recent success of using deep generative models for inverse problems.


page 1

page 2

page 3

page 4


Lower Bounds for Compressed Sensing with Generative Models

The goal of compressed sensing is to learn a structured signal x from a ...

Robust one-bit compressed sensing with non-Gaussian measurements

We study memoryless one-bit compressed sensing with non-Gaussian measure...

Beyond Independent Measurements: General Compressed Sensing with GNN Application

We consider the problem of recovering a structured signal 𝐱∈ℝ^n from noi...

Semi-Random Sparse Recovery in Nearly-Linear Time

Sparse recovery is one of the most fundamental and well-studied inverse ...

Just Least Squares: Binary Compressive Sampling with Low Generative Intrinsic Dimension

In this paper, we consider recovering n dimensional signals from m binar...

Information-Theoretic Lower Bounds for Compressive Sensing with Generative Models

The goal of standard compressive sensing is to estimate an unknown vecto...

Solving Bilinear Inverse Problems using Deep Generative Priors

This paper proposes a new framework to handle the bilinear inverse probl...