Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

CIS Project 22359, Final Technical Report. Discretized Posterior Approximation in High Dimensions

Technical Report ·
DOI:https://doi.org/10.2172/1820564· OSTI ID:1820564
 [1];  [1]
  1. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

Our primary aim in this work is to understand how to efficiently obtain reliable uncertainty quantification in automatic learning algorithms with limited training datasets. Standard approaches rely on cross-validation to tune hyper parameters. Unfortunately, when our datasets are too small, holdout datasets become unreliable—albeit unbiased—measures of prediction quality due to the lack of adequate sample size. We should not place confidence in holdout estimators under conditions wherein the sample variance is both large and unknown. More poigniantly, our training experiments on limited data (Duersch and Catanach, 2021) show that even if we could improve estimator quality under these conditions, the typical training trajectory may never even encounter generalizable models.

Research Organization:
Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA)
DOE Contract Number:
NA0003525
OSTI ID:
1820564
Report Number(s):
SAND2021-11478; 699432
Country of Publication:
United States
Language:
English

Similar Records

A Conditional Autoencoder for Galaxy Photometric Parameter Estimation
Journal Article · Tue Apr 26 00:00:00 EDT 2022 · Publications of the Astronomical Society of the Pacific · OSTI ID:1979376

Efficient Generalizable Deep Learning
Technical Report · Sat Sep 01 00:00:00 EDT 2018 · OSTI ID:1760400

HYPHY: Deep Generative Conditional Posterior Mapping of Hydrodynamical Physics
Journal Article · Sun Dec 11 23:00:00 EST 2022 · The Astrophysical Journal · OSTI ID:1986013

Related Subjects