Conformalized randomized prior operators give per-location calibrated uncertainty intervals for wavelet and spiking wavelet neural operators, with a Gaussian process extension for zero-shot super-resolution UQ.
Machine learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Distribution free uncertainty quantification in neuroscience-inspired deep operators
Conformalized randomized prior operators give per-location calibrated uncertainty intervals for wavelet and spiking wavelet neural operators, with a Gaussian process extension for zero-shot super-resolution UQ.