TY - GEN
T1 - Surrogate regret bounds for proper losses
AU - Reid, Mark D.
AU - Williamson, Robert C.
PY - 2009
Y1 - 2009
N2 - We present tight surrogate regret bounds for the class of proper (i.e., Fisher consistent) losses. The bounds generalise the margin-based bounds due to Bartlett et al. (2006). The proof uses Taylor's theorem and leads to new representations for loss and regret and a simple proof of the integral representation of proper losses. We also present a different formulation of a duality result of Bregman divergences which leads to a simple demonstration of the convexity of composite losses using canonical link functions.
AB - We present tight surrogate regret bounds for the class of proper (i.e., Fisher consistent) losses. The bounds generalise the margin-based bounds due to Bartlett et al. (2006). The proof uses Taylor's theorem and leads to new representations for loss and regret and a simple proof of the integral representation of proper losses. We also present a different formulation of a duality result of Bregman divergences which leads to a simple demonstration of the convexity of composite losses using canonical link functions.
UR - http://www.scopus.com/inward/record.url?scp=71149121122&partnerID=8YFLogxK
M3 - Conference contribution
SN - 9781605585161
T3 - Proceedings of the 26th International Conference On Machine Learning, ICML 2009
SP - 897
EP - 904
BT - Proceedings of the 26th International Conference On Machine Learning, ICML 2009
T2 - 26th International Conference On Machine Learning, ICML 2009
Y2 - 14 June 2009 through 18 June 2009
ER -