# Quantized Compressed Sensing with Score-Based Generative Models

@article{Meng2022QuantizedCS,
title={Quantized Compressed Sensing with Score-Based Generative Models},
author={Xiangming Meng and Yoshiyuki Kabashima},
journal={ArXiv},
year={2022},
volume={abs/2211.13006}
}
• Published 2 November 2022
• Computer Science
• ArXiv
We consider the general problem of recovering a high-dimensional signal from noisy quantized measurements. Quantization, especially coarse quantization such as 1-bit sign measurements, leads to severe information loss and thus a good prior knowledge of the unknown signal is helpful for accurate recovery. Motivated by the power of score-based generative models (SGM, also known as diffusion models) in capturing the rich structure of natural signals beyond simple sparsity, we propose an…
2 Citations

## Figures and Tables from this paper

• Computer Science
ArXiv
• 2022
An unsupervised general-purpose sampling approach called diffusion model based posterior sampling (DMPS) to reconstruct the unknown signal from noisy linear measurements and achieves highly competitive or even better performances on various tasks while being 3 times faster than the leading competitor.
• Computer Science
ArXiv
• 2023
An improved version of QCS-SGM, which is based on a Bayesian inference perspective of the likelihood score computation, whereby an expectation propagation algorithm is proposed to approximately compute the likelihood scores, which works well for general matrices.

## References

SHOWING 1-10 OF 79 REFERENCES

• Computer Science, Mathematics
ICML
• 2020
It is demonstrated that the Binary $\epsilon$-Stable Embedding property, which characterizes the robustness of the reconstruction to measurement errors and noise, also holds for 1-bit compressive sensing with Lipschitz continuous generative models with sufficiently many Gaussian measurements.
• Computer Science
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 2022
This paper aims to estimate the direction of an underlying signal from its nonlinear observations following the semi-parametric single index model (SIM), and shows that the non-iterative method significantly outperforms a state-of-the-art iterative method in terms of both accuracy and efficiency.
• Computer Science
ICML
• 2017
This work shows how to achieve guarantees similar to standard compressed sensing but without employing sparsity at all, and proves that, if G is L-Lipschitz, then roughly O(k log L) random Gaussian measurements suffice for an l2/l2 recovery guarantee.
• Computer Science
ICML
• 2021
The posterior sampling estimator for deep generative priors is implemented using Langevin dynamics, and it is empirically found that it produces accurate estimates with more diversity than MAP.
• Computer Science
IEEE Transactions on Information Theory
• 2011
A new class of convex optimization programs, or decoders, coined Basis Pursuit DeQuantizer of moment p (BPDQp), that model the quantization distortion more faithfully than the commonly used Basis pursuit DeNoise (B PDN) program are presented.
• Computer Science
ICML
• 2019
Borrowing insights from the CS perspective, a novel way of improving GANs using gradient information from the discriminator is developed and it is shown that Generative Adversarial Nets (GANs) can be viewed as a special case in this family of models.
• Computer Science
2008 42nd Annual Conference on Information Sciences and Systems
• 2008
This paper reformulates the problem by treating the 1-bit measurements as sign constraints and further constraining the optimization to recover a signal on the unit sphere, and demonstrates that this approach performs significantly better compared to the classical compressive sensing reconstruction methods, even as the signal becomes less sparse and as the number of measurements increases.
• Computer Science
IEEE Transactions on Information Theory
• 2013
This paper investigates an alternative CS approach that shifts the emphasis from the sampling rate to the number of bits per measurement, and introduces the binary iterative hard thresholding algorithm for signal reconstruction from 1-bit measurements that offers state-of-the-art performance.
• Computer Science
COLT
• 2016
Algorithms with nearly optimal guarantees for both problems under two realistic noise models, bounded (Massart) noise and adversarial (agnostic) noise, when the measurements x_i’s are drawn from any isotropic log-concave distribution are introduced.
• Computer Science
ArXiv
• 2013
It is shown that the signal recovery performance predicted by the replica method under the replica symmetric ansatz is in good consistency with experimental results of an approximate recovery algorithm developed earlier, suggesting that the l1-based recovery problem typically has many local optima of a similar recovery accuracy.