Tensor Product Kernels for Independence
Hilbert-Schmidt independence criterion (HSIC) is among the most widely-used approaches in machine learning and statistics to measure the independence of random variables. Despite its popularity and success in numerous applications, quite little is known about when HSIC characterises independence. I am going to provide a complete answer to this question, with conditions which are often easy to verify in practice.
This talk is based on joint work with Bharath Sriperumbudur.
Zoltan Szabo is a Professor of Data Science at the Department of Statistics, London School of Economics. His research interest is statistical machine learning with focus on kernel methods, information theory, scalable computation, and their applications. Zoltan serves/served as an Area Chair at ICML, NeurIPS, COLT, AISTATS, UAI, IJCAI, ICLR, and the moderator of statistical machine learning (stat.ML) on arXiv. For further details, please see his website (https://zoltansz.github.io/).