Learning minimal volume uncertainty ellipsoids

Itai Alon, David Arnon, Ami Wiesel

Research output: Contribution to journalArticlepeer-review

Abstract

We consider the problem of learning uncertainty regions for parameter estimation problems. The regions are ellipsoids that minimize the average volumes subject to a prescribed coverage probability. As expected, under the assumption of jointly Gaussian data, we prove that the optimal ellipsoid is centered around the conditional mean and shaped as the conditional covariance matrix. In more practical cases, we propose a differentiable optimization approach for approximately computing the optimal ellipsoids using a neural network with proper calibration. Compared to existing methods, our network requires less storage and less computations in inference time, leading to accurate yet smaller ellipsoids. We demonstrate these advantages on four real-world localization datasets.

Original languageAmerican English
Pages (from-to)1-5
Number of pages5
JournalIEEE Signal Processing Letters
DOIs
StateAccepted/In press - 2024

Bibliographical note

Publisher Copyright:
IEEE

Keywords

  • Calibration
  • Covariance matrices
  • Ellipsoids
  • Estimation
  • Shape
  • Training
  • Uncertainty
  • Uncertainty ellipsoid
  • conformal prediction
  • covariance estimation

Fingerprint

Dive into the research topics of 'Learning minimal volume uncertainty ellipsoids'. Together they form a unique fingerprint.

Cite this