Matthias W. Seeger
homepage:http://people.epfl.ch/matthias.seeger
search externally:   Google Scholar,   Springer,   CiteSeer,   Microsoft Academic Search,   Scirus ,   DBlife

Description

Matthias W. Seeger received the Diplom degree (distinction) from Karlsruhe university, Germany, in 1999, his Ph.D. from Edinburgh university, UK, in 2003. He was a research fellow with Michael Jordan and Peter Bartlett, UC Berkeley, from 2003, and with Bernhard Schoelkopf, Max Planck Institute, Tuebingen, Germany, from 2005. He led a research group at Saarbruecken university, Germany, from 2008. He has joined EPFL in fall 2010.

Matthias Seeger made seminal contributions to theory and practice of Gaussian processes in machine learning, PAC-Bayesian learning theory, and large scale variational approximate Bayesian inference. He was invited fellow at the Newton institute program on high-dimensional statistics in 2008. He served in senior program committees of leading machine learning conferences (NIPS 2004, 2010; UAI 2009; AISTATS 2010; ICML 2011).

His research interests are in probabilistic Bayesian machine learning, large scale variational inference and nonparametric GP methods, with applications to image processing and imaging.


Lectures:

lecture
flag Bayesian experimental design
as author at  NIPS Workshops, Lake Tahoe 2013,
79 views
  invited talk
flag Gaussian Variances and Large Scale Bayesian Inference
as author at  Probabilistic Numerics,
167 views
invited talk
flag Bounding the Gaussian Process Information Gain: Applications to PAC-Bayes and GP Bandit Optimization
as author at  PASCAL Foundations and New Trends of PAC Bayesian Learning, London 2010,
383 views
  debate
flag Final Discussion
as author at  Workshops,
37 views
opening
flag Introduction and General Problem Statement
as author at  Workshops,
382 views
  lecture
flag Variational Inference and Experimental Design for Sparse Linear Models
as author at  Workshop on Sparsity and Inverse Problems in Statistical Theory and Econometrics, Berlin 2008,
together with: Hannes Nickisch,
386 views
lecture
flag Information consistency of nonparametric Gaussian process methods
as author at  Workshops,
144 views
  lecture
flag Compressed Sensing and Bayesian Experimental Design
as author at  25th International Conference on Machine Learning (ICML), Helsinki 2008,
together with: Hannes Nickisch,
1611 views
lecture
flag Introduction to the Workshop
as author at  NIPS Workshop on Approximate Bayesian Inference in Continuous/Hybrid Models, Whistler 2007,
197 views
  lecture
flag Experimental Design for Efficient Identification of Gene Regulatory Networks using Sparse Bayesian Models
as author at  Workshop on Parameter Estimation in Systems Biology, Manchester 2007,
458 views