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...
Wee Sun Lee, Peter L. Bartlett, Robert C. Williams...
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...
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...
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...
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...