Skip to search boxSkip to navigationSkip to main content

Prediction with expert evaluators' advice

  • Alexey Chernov
    ,
  • Vladimir Vovk
Research Output: Chapter in Book/Report/Conference proceeding Conference contribution Peer-review

Abstract

We introduce a new protocol for prediction with expert advice in which each expert evaluates the learner’s and his own performance using a loss function that may change over time and may be different from the loss functions used by the other experts. The learner’s goal is to perform better or not much worse than each expert, as evaluated by that expert, for all experts simultaneously. If the loss functions used by the experts are all proper scoring rules and all mixable, we show that the defensive forecasting algorithm enjoys the same performance guarantee as that attainable by the Aggregating Algorithm in the standard setting and known to be optimal. This result is also applied to the case of “specialist” experts. In this case, the defensive forecasting algorithm reduces to a simple modification of the Aggregating Algorithm.

Publication Information

Output type

Research Output: Chapter in Book/Report/Conference proceeding Conference contribution Peer-review

Original language

English

Pages from-to (Number of pages)

Pages 8-22

Publication milestones

  • Published - 01/01/2009

Publication status

Published - 01/01/2009

Publisher

Springer, Japan, India, Australia, Germany, United States, United Arab Emirates, Austria, Switzerland, Italy, China, United Kingdom, Netherlands, Brazil, France, Singapore

ISBN (Print)

9783642044137

ISBN (Electronic)

9783642044137

External Publication IDs

  • handle.net: 10547/279180
  • Scopus: 77952020944

Host publication title

Algorithmic Learning Theory

Access to documents

Publication metrics