Statistics/Finance Seminar with Myrto Limnios, EPFL

The Department of Finance and Center for Statistics are proud to announce the upcoming seminar with Myrto Limnios, EPFL.

Myrto Limnios will present: Learning to Rank in High Dimensions with Applications in Hypothesis Testing

Abstract:
Ranking (multidimensional) random observations has become essential to many data analysis problems, ranging from recommendation systems, computational biology, to information retrieval for instance. The information acquisition processes often involve various and poorly controlled sources in addition, leading to datasets with possibly strong sampling bias. The ability to rank observations in high dimensions is, thus, the subject of much attention, especially due to the lack of natural relation order in the underlying space preventing from simple generalizations. 

In this talk, we will discuss an approach for ranking random observations of complex structure, when drawn from two unknown and independent distributions, relying on a generalization of two-sample linear rank statistics using bipartite ranking. We will show how this new class encompasses, and naturally extends classic univariate rank test statistics, namely for testing statistical homogeneity or independence. We will relate those problems to the concept of Receiver Operating Characteristic (ROC) curve, and provide probabilistic finite-sample uniform guarantees of the testing errors. Convincing experimental studies will illustrate the advantages of this approach compared to state-of-the art methods. 

This is a joint work with S. Clémençon (Télécom Paris) and N. Vayatis (ENS Paris-Saclay).

Location:
Solbjerg Plads 3
2000 Frederiksberg
Room: SPs03