Speaker: Prof. Visa Koivunen
Dept of Signal Processing & Acoustics, Aalto University, Finland
Abstract: This talk addresses the problem of performing statistical interference for large-scale data sets i.e., Big Data. The volume and dimensionality of the data may be so high that it cannot be processed or stored in a single computing node. We propose a scalable, statistically robust and computationally efficient bootstrap method, compatible with this issue to processing and storage systems. The proposed method combines distributed bootstrap with computationally efficient fixed point equations. Many statistically robust and highly efficient estimators lend themselves to such computation. Bootstrap we samples are constructed from a smaller number of distinct data points that correspond to multiple disjointed subsets of data, similarly to the bag of Little Bush got methods(BLB) by Kleiner et al. This facilitates distributed storage and computation in inference. Significant savings in computation is achieved by avoiding the re-computation of the estimator for each straps sample. Instead, an initial estimate is improved by using an efficient fixed-point estimation equation. An analytically found correction term compensating for underestimated variability is applied. Our propose the bootstrapped method facilitates the use of highly robust statistical methods in analyzing large-scale data sets. The favorable statistical properties of the method are established analytically. Numerical examples on finding the confidence intervals in parameter estimation and hypothesis testing problems demonstrate scalability, low complexity, and robust statistical performance of the method in analyzing large data sets.
Biography:
Visa Koivunen (IEEE Fellow) received his D.Sc (EE) degree with honors from that university of Oulu, Department of Electrical Engineering. He received the Primus doctor (best graduate) award among the doctoral graduates in years 1989-1994. He is a member of Eta Kappa Nu and member of IEEE for 30 years (become student member 1986). From 1992 to 1995 he was a visiting researcher at the University of Pennsylvania Philadelphia USA. Years 1997-1999 he was faculty atTempere, UT. Since 1999 he has been a full professor of signal processing at Aalto University (formerly known as Helsinki University of technology), Finland. He is one of the principal investigators in SMARAD Center of Excellence in Research nominated by the Academy of Finland. Years 2003 to 2006 he was also adjunct full professor at the University of Pennsylvania Philadelphia USA. During his sabbatical term 2006 to 2007 he was a visiting professor at Princeton University NJ USA. He has also been a part time visiting fellow at Nokia Research Center(2006-2012). He spent another sabbatical at Princeton University for the full academic year 2013-2014. He has had continuing visiting fellow appointment at Princeton University since 2010 and works there for 1 to 3 months every year.
Dr. Koivunen's research interest Include statistical, communications, sensor array and multichannel signal processing as well as large-scale data analysis. He has published more than 380 papers in international Scientific conferences and journals and holds six patents. He co-authored the papers receiving the best paper award in IEEE PIMRC 2005, EUSIPCO'2006, EUCAP (European Conference on Antennas and Propagation) 2006 an COCORA 2012. He has been awarded the IEEE Signal Processing Society best paper award for the year 2007 (with J. Eriksson). He has served as an associate editor for IEEE Signal Processing Letters, IEEE Transactions on Signal Processing, Signal Processing and Journal of Wireless Communication and Networking. He has also served as co-editor 42 IEEE JS TSP special issues. He was a member of editorial board for a IEEE Signal Processing Magazine. He has been a member of the IEEE signal processing Society technical committee SPCOM-TC (2 terms) and SAM-TC (2 terms) as well as an industrial relations board. He was the general chair of the IEEE SPAWC conference 2007 conference in Helsinki, Finland June 2007 and Technical Program Chair for the IEEE SPWC 2015 Asilomar Conference. He has served as IEEE SPS distinguished lecture for the years 2015 to 2016. He has been awarded the 2015 EURASIP (European Association for Signal Processing) Technical Achievement Award for fundamental contributions to statistical signal processing and its applications in wireless communications, radar and related fields. He is a member of the IEEE Joseph Fourier Award committee.
Dr. Visa Koivunen, Academy Professor, Aalto University, Finland
email: visa.koivunen@aalto.fi
website: https://people.aalto.fi/new/vias.koivunen
Guest's faculty host is EECS Prof. Lee Swindlehurst, swindle@uci.edu, 949-824-1895
Four building and parking information please visit https://communiations.uci.edu/documents/pdf/UCI_15_map_campus.pdf
McDonnell Douglas Engineering Auditorium (MDEA) is Bldg#311 (F6) on campus map
Park in Anteater Parking Structure APS (E7)
If you need additional information, please call the EECS business office at 949-824-5489.