Builtin vs. auxiliary detection of extrapolation risk.

PDF Version Also Available for Download.

Description

A key assumption in supervised machine learning is that future data will be similar to historical data. This assumption is often false in real world applications, and as a result, prediction models often return predictions that are extrapolations. We compare four approaches to estimating extrapolation risk for machine learning predictions. Two builtin methods use information available from the classification model to decide if the model would be extrapolating for an input data point. The other two build auxiliary models to supplement the classification model and explicitly model extrapolation risk. Experiments with synthetic and real data sets show that the auxiliary ... continued below

Physical Description

36 p.

Creation Information

Munson, Miles Arthur & Kegelmeyer, W. Philip, February 1, 2013.

Context

This report is part of the collection entitled: Office of Scientific & Technical Information Technical Reports and was provided by UNT Libraries Government Documents Department to Digital Library, a digital repository hosted by the UNT Libraries. More information about this report can be viewed below.

Who

People and organizations associated with either the creation of this report or its content.

Sponsor

Publisher

  • Sandia National Laboratories
    Publisher Info: Sandia National Laboratories (SNL-CA), Livermore, CA (United States)
    Place of Publication: Livermore, California

Provided By

UNT Libraries Government Documents Department

Serving as both a federal and a state depository library, the UNT Libraries Government Documents Department maintains millions of items in a variety of formats. The department is a member of the FDLP Content Partnerships Program and an Affiliated Archive of the National Archives.

Contact Us

What

Descriptive information to help identify this report. Follow the links below to find similar items on the Digital Library.

Description

A key assumption in supervised machine learning is that future data will be similar to historical data. This assumption is often false in real world applications, and as a result, prediction models often return predictions that are extrapolations. We compare four approaches to estimating extrapolation risk for machine learning predictions. Two builtin methods use information available from the classification model to decide if the model would be extrapolating for an input data point. The other two build auxiliary models to supplement the classification model and explicitly model extrapolation risk. Experiments with synthetic and real data sets show that the auxiliary models are more reliable risk detectors. To best safeguard against extrapolating predictions, however, we recommend combining builtin and auxiliary diagnostics.

Physical Description

36 p.

Language

Item Type

Identifier

Unique identifying numbers for this report in the Digital Library or other systems.

  • Report No.: SAND2013-2534
  • Grant Number: AC04-94AL85000
  • Office of Scientific & Technical Information Report Number: 1095941
  • Archival Resource Key: ark:/67531/metadc838699

Collections

This report is part of the following collection of related materials.

Office of Scientific & Technical Information Technical Reports

Reports, articles and other documents harvested from the Office of Scientific and Technical Information.

Office of Scientific and Technical Information (OSTI) is the Department of Energy (DOE) office that collects, preserves, and disseminates DOE-sponsored research and development (R&D) results that are the outcomes of R&D projects or other funded activities at DOE labs and facilities nationwide and grantees at universities and other institutions.

What responsibilities do I have when using this report?

When

Dates and time periods associated with this report.

Creation Date

  • February 1, 2013

Added to The UNT Digital Library

  • May 19, 2016, 9:45 a.m.

Description Last Updated

  • Feb. 17, 2017, 4:19 p.m.

Usage Statistics

When was this report last used?

Yesterday: 0
Past 30 days: 0
Total Uses: 3

Interact With This Report

Here are some suggestions for what to do next.

Start Reading

PDF Version Also Available for Download.

International Image Interoperability Framework

IIF Logo

We support the IIIF Presentation API

Munson, Miles Arthur & Kegelmeyer, W. Philip,. Builtin vs. auxiliary detection of extrapolation risk., report, February 1, 2013; Livermore, California. (digital.library.unt.edu/ark:/67531/metadc838699/: accessed October 19, 2018), University of North Texas Libraries, Digital Library, digital.library.unt.edu; crediting UNT Libraries Government Documents Department.