Share Email Print

Proceedings Paper

Lessons from learning theory for benchmark design
Author(s): John Langford
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This discussion/tutorial consists of a few short discussions on the (theoretical) trade-offs of various choices in constructing benchmarks. Most of the results discussed here are "common sense" at high level. However, all of this "common sense" is (to some extent) quantifiable common sense, and occasionally that quantification is useful. These short discussions cover: 1) Prediction Domains & Loss functions, 2) Prediction settings, 3) Assumption Failures.

Paper Details

Date Published: 2 September 2004
PDF: 8 pages
Proc. SPIE 5427, Algorithms for Synthetic Aperture Radar Imagery XI, (2 September 2004); doi: 10.1117/12.555674
Show Author Affiliations
John Langford, Toyota Technological Institute at Chicago (United States)

Published in SPIE Proceedings Vol. 5427:
Algorithms for Synthetic Aperture Radar Imagery XI
Edmund G. Zelnio; Frederick D. Garber, Editor(s)

© SPIE. Terms of Use
Back to Top