ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2310.09999
14
3

Outlier Detection Using Generative Models with Theoretical Performance Guarantees

16 October 2023
Jirong Yi
A. D. Le
Tianming Wang
Xiaodong Wu
Weiyu Xu
ArXivPDFHTML
Abstract

This paper considers the problem of recovering signals modeled by generative models from linear measurements contaminated with sparse outliers. We propose an outlier detection approach for reconstructing the ground-truth signals modeled by generative models under sparse outliers. We establish theoretical recovery guarantees for reconstruction of signals using generative models in the presence of outliers, giving lower bounds on the number of correctable outliers. Our results are applicable to both linear generator neural networks and the nonlinear generator neural networks with an arbitrary number of layers. We propose an iterative alternating direction method of multipliers (ADMM) algorithm for solving the outlier detection problem via ℓ1\ell_1ℓ1​ norm minimization, and a gradient descent algorithm for solving the outlier detection problem via squared ℓ1\ell_1ℓ1​ norm minimization. We conduct extensive experiments using variational auto-encoder and deep convolutional generative adversarial networks, and the experimental results show that the signals can be successfully reconstructed under outliers using our approach. Our approach outperforms the traditional Lasso and ℓ2\ell_2ℓ2​ minimization approach.

View on arXiv
Comments on this paper