- Thesis:
- Bachelor in Mathematics
- Author:
- Robin Viellieber
- Title:
- Optimal rates of aggregation in classification
- Supervisor:
- Jan JOHANNES
- Abstract:
- Using an aggregation procedure, this thesis aims to establish optimal rates of convergence for four aggregates in the context of classification. The here stated results rely on a low noise assumption and are provided with respect to the Bayes rule. However, we will construct the theory using the convex hinge loss and then derive similar results for the Bayes rule. Moreover, we introduce an approach to optimality based on Tsybakov (2003).
References:- G. Lecué. Optimal rates of aggregation in classification under low noise assumption. Bernoulli, 13(4):1000-1022, 2007.
- A. B. Tsybakov. Optimal rates of aggregation. In: Schölkopf, Bernhard (ed.) et al., Learning theory and kernel machines. 16th annual conference on learning theory and 7th Kernel workshop proceedings. Springer Lecture Notes Computer Science, 2777, 303-313, 2003.