NEW APPROACHES TO STATISTICAL LEARNING THEORY

By OLIVlER 13OUSQUET. 2006

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Interpretable Distribution Features with Maximum Testing Power (2016, background): “, without S−1 n ) was shown by Chwialkowski et al. (2015) to be a metric on the space of probability measures for any V .”
Margin-based Ranking and an Equivalence between AdaBoost and RankBoost (2009, background): “A number of papers, including those of Cortes and Mohri (2004) and Caruana and Niculescu-Mizil (2006) have noted that in fact, AdaBoost experimentally seems to be very good at the bipartite ranking problem, even though it was RankBoost that was explicitly designed to solve this problem, not AdaBoost”
Machine learning with operational costs (2011, background): “On the other hand, for a practitioner, every prior belief should reduce the number of instances they need to collect (these may be expensive to obtain) and thus constants (even their approximate values) become important (Bousquet, 2003).”
Concentration Inequalities (2008, unknown): “As it turns out, this inequality remains true for a large class of convex functions φ, see Beckner [64], Lataa la and Oleszkiewicz [65], Ledoux [20], Boucheron, Bousquet , Lugosi, and Massart [29], and Chafa¨ı [66].”
Practical Ensemble Classification Error Bounds for Different Operating Points (2013, background): “Thus, classification requirements are different than they would be for a classifier operating by itself and induce objectives besides zero-one loss.”
The P-Norm Push: A Simple Convex Ranking Algorithm that Concentrates at the Top of the List (2009, methodology): “This work is inspired by the works of Koltchinskii and Panchenko (2002), Cuckerand Smale (2002), and Bousquet (2003).”