Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Quantifying uncertainty in online regression forests
RISE - Research Institutes of Sweden (2017-2019), ICT, SICS.ORCID iD: 0000-0002-8180-7521
ISI Foundation, Italy.
KTH Royal Institute of Technology, Sweden.
2019 (English)In: Journal of machine learning research, ISSN 1532-4435, E-ISSN 1533-7928, Vol. 20Article in journal (Refereed) Published
Abstract [en]

Accurately quantifying uncertainty in predictions is essential for the deployment of machine learning algorithms in critical applications where mistakes are costly. Most approaches to quantifying prediction uncertainty have focused on settings where the data is static, or bounded. In this paper, we investigate methods that quantify the prediction uncertainty in a streaming setting, where the data is potentially unbounded. We propose two meta-algorithms that produce prediction intervals for online regression forests of arbitrary tree models; one based on conformal prediction, and the other based on quantile regression. We show that the approaches are able to maintain specified error rates, with constant computational cost per example and bounded memory usage. We provide empirical evidence that the methods outperform the state-of-the-art in terms of maintaining error guarantees, while being an order of magnitude faster. We also investigate how the algorithms are able to recover from concept drift. ©c 2019 Theodore Vasiloudis, Gianmarco De Francisci Morales, Henrik Boström.

Place, publisher, year, edition, pages
Microtome Publishing , 2019. Vol. 20
Keywords [en]
Decision Trees, Online learning, Regression, Uncertainty, Forecasting, Forestry, Learning algorithms, Reactor cores, Regression analysis, Uncertainty analysis, Conformal predictions, Critical applications, Prediction interval, Prediction uncertainty, Quantile regression, Machine learning
National Category
Natural Sciences
Identifiers
URN: urn:nbn:se:ri:diva-43366Scopus ID: 2-s2.0-85077516171OAI: oai:DiVA.org:ri-43366DiVA, id: diva2:1389371
Available from: 2020-01-29 Created: 2020-01-29 Last updated: 2020-01-29Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Scopushttp://jmlr.csail.mit.edu/papers/volume20/19-006/19-006.pdf

Authority records BETA

Vasiloudis, Theodore

Search in DiVA

By author/editor
Vasiloudis, Theodore
By organisation
SICS
In the same journal
Journal of machine learning research
Natural Sciences

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 10 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
v. 2.35.10