Plenary Speakers

-Inhomogeneous Large-Scale Data: Maximin Effects and their Statistical Estimation
Peter Bühlmann
, Swiss Federal Institute of Technology, Zurich

Large-scale or "big" data usually refers to scenarios with potentially very many variables (dimension p) and very large sample size n. Such data is most often of "inhomogeneous" nature, i.e., neither being i.i.d. realizations from a distribution nor being generated from a stationary distribution. We propose a new methodology for some class of large-scale inhomogeneous data, in terms of so-called maximin effects which optimize performance in the most adversarial constellation. The advocated procedure is computationally efficient and under certain circumstances orders of magnitudes faster than standard penalized regression estimators, and we provide statistical accuracy guarantees for scenarios where n and/or p are large.


-Scalable Bayesian Model Selection Methods
Xuming He, University of Michigan, USA

Bayesian model selection faces challenges both in theory and in computation when the number of potential covariates p is large. We propose a Bayesian variable selection method for logistic regression that adapts to both the sample size n and the number of potential covariates p with two important features. First, it has strong model selection consistency even when p is large. Second, we propose a new Gibbs sampler that does not require p2 operations in each of its iterations. In contrast with the standard Gibbs sampler which requires sampling from a p dimensional multivariate normal distribution with a non-sparse covariance matrix, our new algorithm is much more scalable to high dimensional problems, both in memory and in computational efficiency. We compare our proposed method with several leading variable selection methods through a simulation study to show that our proposed approach selects the correct model with higher probabilities than most competitors. The talk is based on ongoing work with Naveen Narisetty and Juan Shen.

-Statistics of Complex Extremes
Anthony Davison, Swiss Federal Institute of Technology, Lausanne:

Statistics of complex extremes, used for example in space-time modelling of rainfall, or extreme river levels and flooding, has developed very rapidly in recent years. A wide variety of techniques are used to fit such models, ranging from MCMC methods, to composite likelihood ideas, to non- and semi-parametric models. In this talk I shall give a rapid review of the area, with particular emphasis on computational aspects.