Conference Papers Year : 2024

Small-Noise Sensitivity Analysis of Locating Pulses in the Presence of Adversarial Perturbation

Abstract

A fundamental small-noise sensitivity analysis of spike localization in the presence of adversarial perturbations and an arbitrary point spread function (PSF) is presented. The analysis leverages the local Lipschitz property of the inverse map from measurement noise to parameter estimate. In the small noise regime, the local Lipschitz constant converges to the spectral norm of the noiseless Jacobian of the inverse map. An interpretable upper bound in terms of the minimum separation of spikes, norms, and flatness of the PSF and its derivative, as well as the distribution of spike amplitudes is provided. Numerical experiments highlighting the relevance of the theoretical bound as a proxy to the local Lipschitz constant and its dependence on the key attributes of the problem are presented.
Fichier principal
Vignette du fichier
SAM_Small_Noise_Sensitivity.pdf (374.84 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Licence
Copyright

Dates and versions

hal-04489137 , version 1 (04-03-2024)
hal-04489137 , version 2 (22-07-2024)

Licence

Copyright

Identifiers

  • HAL Id : hal-04489137 , version 2

Cite

Meghna Kalra, Maxime Ferreira Da Costa, Kiryung Lee. Small-Noise Sensitivity Analysis of Locating Pulses in the Presence of Adversarial Perturbation. IEEE 13th Sensor Array and Multichannel Signal Processing Workshop, Jul 2024, Corvallis, United States. ⟨hal-04489137v2⟩
134 View
70 Download

Share

More