Stochastics and statistics
Stochastic analysis and statistical modeling are key methodologies for analyzing random interactions in today's information systems. Our research group applies and develops methods in probability theory and mathematical statistics related to applications in communication and transportation networks, engineering, and natural sciences. The main research areas are: stochastic networks and queueing systems, asymptotic statistics, and random spatial structures.
We teach courses in probability and statistics at all levels. Many of the offered MSc courses are eligible as a basis for an SHV degree in insurance mathematics. PhD education in stochastics and statistics is coordinated by the Finnish Doctoral Education Network in Stochastics and Statistics (FDNSS).
MSc/PhD courses in spring 2016
BSc courses in spring 2016
Affiliated postdocs: Steven Flores (University of Helsinki), Giancarlo Pastor (VTT Research Centre), Lauri Viitasaari (University of Saarbrücken).
Affiliated PhD students: Mikko Kuronen (University of Jyväskylä), Matias Leppisaari (Model IT), Eveliina Peltola (University of Helsinki), Mika Sirviö (Insurance Centre), Tarja Sirén (Financial Supervisory Authority).
Affiliated docents: Kari Eloranta, Teemu Pennanen (King's College London), Karl Sigman (Columbia University).
Aalto Stochastics Wiki
Giancarlo Pastor Figueroa 1.3.2016–31.8.2017
- 20.6. 15:15 Laurie Field (EPFL): TBA – M3 (M234)
- 6.6. 15:15 Klaus Nordhausen (University of Turku): SOBI for the separation of uncorrelated stationary time series – M3 (M234)
In the second order source separation model is assumed that the observed p-variate time series are linear combinations of p latent uncorrelated weakly stationary time series with different time dependence structures. The aim is to find an estimate for an unmixing matrix, which then transforms the observed time series back to the uncorrelated latent time series. The classical approach to estimate the unmixing matrix uses approximate joint diagonalization of several autocovariance matrices with different lags and is called SOBI.
In this talk some recent results regarding the statistical properties of SOBI are presented and it is shown how these results can be used to choose the best lag set out of a finite set of candidate sets specified by the user.
- J Barral, A Kupiainen, M Nikula, E Saksman, C Webb. Basic properties of critical lognormal multiplicative chaos. The Annals of Probability 43(5):2205-2249, 2015.
- P Aalto, L Leskelä. Information spreading in a large population of active transmitters and passive receivers. SIAM Journal on Applied Mathematics 75(5):1965–1982, 2015.
- E Azmoodeh, L Viitasaari. Rate of convergence for discretization of integrals with respect to fractional Brownian motion. Journal of Theoretical Probability, 28(1):396-422, 2015.
- C Hongler, K Kytölä. Ising interfaces and free boundary conditions. Journal of the American Mathematical Society 26:1107–1189, 2013.
- P Ilmonen, D Paindaveine. Semiparametrically efficient inference based on signed ranks in symmetric independent component models. Annals of Statistics 39(5):2448–2476, 2011.
Helena Aro (Etera)
Ehsan Azmoodeh (University of Luxembourg)
Milla Kibble (FIMM Institute for Molecular Medicine Finland)
Matti Kiiski (ETH Zürich)
Ilkka Mellin (University teacher emeritus)
Igor Morlanes (Stockholm University)
Amitava Mukherjee (XLRI- Xavier School of Management)
Ari-Pekka Perkkiö (Technische Universität Berlin)
Heikki Tikanmäki (Finnish Centre for Pensions)
Esko Valkeila (1951–2012)
Page content by: webmaster-math [at] list [dot] aalto [dot] fi