13 search results - page 1 / 3 » The Importance of Convexity in Learning with Squared Loss |
TIT
1998
13 years 4 months ago
1998
We show that if the closureof a function class F under the metric induced by some probability distribution is not convex, then the sample complexity for agnostically learning F wi...
NIPS
2008
13 years 6 months ago
2008
Bartlett et al (2006) recently proved that a ground condition for convex surrogates, classification calibration, ties up the minimization of the surrogates and classification risk...
SDM
2008
SIAM
13 years 6 months ago
2008
SIAM
This paper presents a stagewise least square (SLS) loss function for classification. It uses a least square form within each stage to approximate a bounded monotonic nonconvex los...
ACL
2008
13 years 6 months ago
2008
We present a novel semi-supervised training algorithm for learning dependency parsers. By combining a supervised large margin loss with an unsupervised least squares loss, a discr...
JMLR
2012
11 years 7 months ago
2012
We prove logarithmic regret bounds that depend on the loss L∗ T of the competitor rather than on the number T of time steps. In the general online convex optimization setting, o...