Tutorials on uncertainty quantification in complex models: Botond Szabo --- Leiden University

Dear all, 

 Dr.  Botond Szabo from the Mathematics department at Leiden university (The
Netherlands), would be visiting the school from the 21 to the 29th of April 2017.  His
research interests covers Nonparametric Bayesian Statistics, Adaptation, Asymptotic
Statistics, Operation research and Graph Theory.  He has kindly accepted to give a two
tutorials (90 minutes each) about recovery and uncertainty quantification in
nonparametric models; and about high dimensional inference and uncertainty
quantification.  The tutorials  will take place in the 535 room (Carslaw
Building, 5th floor) Monday 24th April at 11am and Wednesday the 26th of April
at 11am.  

He will also give a seminar on Friday 28th April (see details below) in Carslaw
173.  

Hope to see many of you there and I would encourage PhD students to attend the tutorials
and the seminar.  

Kind regards, 

Lamiae.  

############################################################################## 

Title: An asymptotic analysis of nonparametric distributed methods 

Abstract 

In the recent years in certain applications datasets have become so large that it
becomes unfeasible, or computationally undesirable, to carry out the analysis on a
single machine.  This gave rise to divide-and-conquer algorithms where the data is
distributed over several "local" machines and the computations are done on these
machines parallel to each other.  Then the outcome of the local computations are somehow
aggregated to a global result in a central machine.  Over the years various
divide-and-conquer algorithms were proposed, many of them with limited theoretical
underpinning.  First we compare the theoretical properties of a (not complete) list of
proposed methods on the benchmark nonparametric signal-in-white-noise model.  Most of
the investigated algorithms use information on aspects of the underlying true signal
(for instance regularity), which is usually not available in practice.  A central
question is whether one can tune the algorithms in a data-driven way, without using any
additional knowledge about the signal.  We show that (a list of) standard data-driven
techniques (both Bayesian and frequentist) can not recover the underlying signal with
the minimax rate.  This, however, does not imply the non-existence of an adaptive
distributed method.  To address the theoretical limitations of data-driven
divide-and-conquer algorithms we consider a setting where the amount of information sent
between the local and central machines is expensive and limited.  We show that it is not
possible to construct data-driven methods which adapt to the unknown regularity of the
underlying signal and at the same time communicates the optimal amount of information
between the machines.  This is a joint work with Harry van Zanten.  

About the speaker: 

Botond Szabo is an Assistant Professor at the University of Leiden, The Netherlands.
Botond received his phd in Mathematical Statistics from the Eindhoven University of
technology, the Netherlands in 2014 under the supervision of Prof.dr.  Harry van Zanten
and Prof.dr.  Aad van der Vaart.  His research interests cover Nonparametric Bayesian
Statistics, Adaptation, Asymptotic Statistics, Operation research and Graph Theory.  He
received the Savage Award in Theory & Methods: Runner up for the best PhD dissertation
in the field of Bayesian statistics and econometrics in the category Theory & Methods
and the "Van Zwet Award" for the best PhD dissertation in the Netherlands in
Statistics and Operation Research 2015.  He is an Associate Editor of Bayesian
Analysis.  You can find more about him here: http://math.bme.hu/~bszabo/index_en.html .