Direkt zum InhaltDirekt zur SucheDirekt zur Navigation
▼ Zielgruppen ▼

Humboldt-Universität zu Berlin - Mathematisch-Naturwissenschaftliche Fakultät - Research Unit 1735

Program

Schedule

 

  Sun, Mar 5 Mon, Mar 6 Tue, Mar 7 Wed, Mar 8 Thu, Mar 9 Fri, Mar 10
Breakfast
08:00-9:00
           

09:00-10:30

  Joel Tropp Joel Tropp Joel Tropp

Lorenzo Rosasco

Lorenzo Rosasco

Break            
11:00-12:30  

Joel Tropp

Lorenzo Rosasco

Giovanni Peccati

Giovanni Peccati

Giovanni Peccati

Lunch
12:30-14:00
          Departure

14:00-16:30

 

  Participants' Introduction Group Exercises Excursion Group Exercises
16:30-18:00 Arrival Research Unit Talks Lorenzo Rosasco
(Discussion of group exercise)

Giovanni Peccati

(Discussion of group exercise)

 
Dinner
18:00-19:00
         
    Poster Session      

 

 

Lecture Series

This year's lecture series will be given by


 

peccati2.jpeg

 

 
Giovanni Peccati

Luxembourg University

 

   

 

       

rosasco.jpeg

 
Lorenzo Rosasco

Massachusetts Institute of Technology

and University of Genoa

   

Tropp.jpg

   
Joel A. Tropp

California Institute of Technology

 
   

 

 

Preparatory material

  • Giovanni Peccati's lectures will in parts be based on material contained in the edited volume Stochastic Analysis for Poisson Point Processes, G. Peccati and M. Reitzner (eds.), Springer, 2016.                                        A forthcoming monograph by G. Last and M. Penrose with "Lectures on the Poisson Process" also contains important material.
  • Joel Tropp's lectures will be based on a subset of the following articles:  

J.A. Tropp (2015): Convex recovery of a structured signal from independent random linear measurements. in: Sampling Theory, a Renaissance, Birkhäuser.

V. Chandrasekaran et al. (2012): Convex geometry of linear inverse problems. Foundations of Computational Mathematics 12, 805-849.

D. Amelunxen et al. (2014): Living on the edge: Phase transitions in convex programs with random data. Available at https://arxiv.org/abs/1303.6672.

M.B. McCoy and J.A. Tropp (2014): From Steiner formulas for cones to concentration of intrinsic volumes. Discrete and Computational Geometry 51, 926-963.

C. Thrampoulidis, S. Oymak, and B. Hassibi (2015): The Gaussian min-max theorem in the presence of convexity. Available at https://arxiv.org/abs/1408.4837.

S. Oymak and J.A. Tropp (2015): Universality laws for randomized dimension reduction, with applications. Available at https://arxiv.org/abs/1511.09433.

C. Thrampoulidis (2016): Recovering structured signals in high-dimensions via non-smooth convex optimization: Precise performance analysis. PhD thesis, available at http://resolver.caltech.edu/CaltechTHESIS:06032016-144604076.

 

Lorenzo Rosasco's notes on Regularization methods in large scale machine learning with exercises at the end.

 

Exercises to Giovanni Peccati's lecturees.

 

Joel Tropp's slides.

 

Poster Session

All participants are encouraged to present their work in a poster session.

 

Participants Short Introduction

All participants briefly introduce themselves and their research interests within about 3 minutes on Monday afternoon, supported by one or at most two slides. Please send your slide(s) by March 1 as a single .pdf-file to for1735.math@lists.uni-hamburg.de.