We consider the problem of deriving class-size independent generalization bounds for some regularized discriminative multi-category classification methods. In particular, we obtai...
A multitask learning framework is developed for discriminative classification and regression where multiple large-margin linear classifiers are estimated for different predictio...
Kernel Ridge Regression (KRR) and the recently developed Kernel Aggregating Algorithm for Regression (KAAR) are regression methods based on Least Squares. KAAR has theoretical adv...
Steven Busuttil, Yuri Kalnishkan, Alexander Gammer...
The notion of algorithmic stability has been used effectively in the past to derive tight generalization bounds. A key advantage of these bounds is that they are designed for spec...
Generalization bounds depending on the margin of a classifier are a relatively recent development. They provide an explanation of the performance of state-of-the-art learning syste...