Saved in:
Bibliographic Details
Main Authors: Miani, Marco, Beretta, Lorenzo, Hauberg, Søren
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.15008
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929557859205120
author Miani, Marco
Beretta, Lorenzo
Hauberg, Søren
author_facet Miani, Marco
Beretta, Lorenzo
Hauberg, Søren
contents Current uncertainty quantification is memory and compute expensive, which hinders practical uptake. To counter, we develop Sketched Lanczos Uncertainty (SLU): an architecture-agnostic uncertainty score that can be applied to pre-trained neural networks with minimal overhead. Importantly, the memory use of SLU only grows logarithmically with the number of model parameters. We combine Lanczos' algorithm with dimensionality reduction techniques to compute a sketch of the leading eigenvectors of a matrix. Applying this novel algorithm to the Fisher information matrix yields a cheap and reliable uncertainty score. Empirically, SLU yields well-calibrated uncertainties, reliably detects out-of-distribution examples, and consistently outperforms existing methods in the low-memory regime.
format Preprint
id arxiv_https___arxiv_org_abs_2409_15008
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Sketched Lanczos uncertainty score: a low-memory summary of the Fisher information
Miani, Marco
Beretta, Lorenzo
Hauberg, Søren
Numerical Analysis
Current uncertainty quantification is memory and compute expensive, which hinders practical uptake. To counter, we develop Sketched Lanczos Uncertainty (SLU): an architecture-agnostic uncertainty score that can be applied to pre-trained neural networks with minimal overhead. Importantly, the memory use of SLU only grows logarithmically with the number of model parameters. We combine Lanczos' algorithm with dimensionality reduction techniques to compute a sketch of the leading eigenvectors of a matrix. Applying this novel algorithm to the Fisher information matrix yields a cheap and reliable uncertainty score. Empirically, SLU yields well-calibrated uncertainties, reliably detects out-of-distribution examples, and consistently outperforms existing methods in the low-memory regime.
title Sketched Lanczos uncertainty score: a low-memory summary of the Fisher information
topic Numerical Analysis
url https://arxiv.org/abs/2409.15008