Collaborative estimation
Dr Onkar Dabeer, Tata Institute of Fundamental Research, India
Abstract
The talk has two parts, both involving pooling of data from different sources to improve the estimation task at hand. In particular, I will emphasize the modeling aspect in both parts, which may be of interest in physical sciences.
1. In e-commerce, we often have access to ratings given by users for many of the items they have bought/experienced. In collaborative filtering, we pool together rating data from different users about different items and use it to make item recommendations for users. We propose a mathematical model to study this problem, identify fundamental performance limits for the model, exhibit schemes that achieve these limits, and test their performance on real data.
2. We consider a collection of prediction experiments, where several experiments may share the same regression parameters (but we do know which experiments are similar). By pooling data across experiments, we hope to do better. In this talk, I will show an application of this framework and discuss some methods to solve the problem.
Show speakers
Dr Onkar Dabeer, Tata Institute of Fundamental Research, India
Dr Onkar Dabeer, Tata Institute of Fundamental Research, India
Onkar Dabeer received the BTech and MTech degrees in Electrical Engineering from the Indian Institute of Technology, Bombay, in 1996 and 1998 respectively, and, the PhD\ degree in Electrical Engineering from the University of California at San Diego in June 2002. He was a postdoctoral researcher at University of California, Santa Barbara from July 2002 to July 2003. From August 2003 to August 2004, he served as a Senior Engineer at Qualcomm Inc, San Diego.
Since September 2004 he has been on the faculty at the School of Technology and Computer Science, Tata Institute of Fundamental Research, Mumbai (Bombay), India. He is an Editor for the IEEE Transactions on Wireless Communications and IEEE Wireless Communications Letter. He is a recipient of the Prof. Revankar Prize for outstanding graduate student (IIT Bombay, 1998), the Homi Bhabha Fellowship (2006-2009), the Indian National Science Academy's Young Scientist Medal (2009), and he is an Associate (2009-2012) of the Indian Academy of Science. His research interests include estimation theory (with current emphasis on problems arising in web, social media, and sensor networks) and multi-Gigabit wireless networks.
Extra-solar planets via a Bayesian multi-planet periodogram
Professor Phil Gregory, University of British Columbia, Canada
Abstract
A remarkable array of new ground based and space based astronomical tools are providing astronomers access to other solar systems. Over 700 planets have been discovered to date including several super earths in the habitable zone. These successes on the part of the observers have spurred a significant effort to improve the statistical tools for analyzing data in this field.
I will describe a Bayesian multi-planet Kepler periodogram based on a new fusion Markov chain Monte Carlo algorithm which incorporates parallel tempering, simulated annealing and genetic crossover operations. Each of these features facilitate the detection of a global minimum in chi-squared in a multi-modal environment. By combining all three, the algorithm greatly increases the probability of realizing this goal.
The fusion MCMC is controlled by a unique two stage adaptive control system that automates the tuning of the proposal distributions for efficient exploration of the model parameter space even when the parameters are highly correlated. This controlled fusion MCMC algorithm is implemented in Mathematica using parallized code and run on an 8 core PC. It is designed to be a very general tool for nonlinear model fitting. The performance of the algorithm will be illustrated with some recent successes in the exoplanet field where it has facilitated the detection of a number of new planets.
Show speakers
Professor Phil Gregory, University of British Columbia, Canada
Professor Phil Gregory, University of British Columbia, Canada
"
Phil Gregory received a PhD in physics from University of Manchester in 1969, specializing in space physics and radio astronomy at the Jodrell Bank Observatory with an experiment on the first all British satellite Ariel III. He returned to Canada in 1970 as a Postdoctoral Fellow in the Astronomy Department of the University of Toronto. In 1972, he discovered the first giant radio outburst emanating from a newly discovered X-ray source Cygnus X-3. A special edition of Nature was devoted to the discovery and follow-up observations. The radio outbursts coincide with the ejection of jets traveling at close to the speed of light emanating from either a black hole or neutron star. The discovery led to a faculty position in the Physics Department of the University of British Columbia in 1973. In 1976, he started the Galactic Radio Patrol Project to search for transient radio sources using the giant Green Bank 300 ft telescope of the US National Radio Astronomy Observatory. The project continued until 1988 when the telescope suddenly collapsed (apparently to prevent him from discovering intelligent life on other worlds!) . Amongst the project discoveries was a new supernova remnant with a central 7s pulsar which was featured on the cover of Nature in 1981. In 1989 he developed a keen interest in Bayesian data analysis which led in 1992 (together with Tom Loredo of Cornell University) to the Gregory-Loredo Bayesian algorithm for the detection of periodic signals of unknown shape. His text book on ""Bayesian logical Data Analysis for the Physical Sciences"" was published by Cambridge University Press (2005 & 2010). He has recently pioneered a very general fusion Markov Chain Monte Carlo Bayesian method for nonlinear model fitting. He is exploiting this new tool in extra-solar planet research where it functions as a multi-planet Kepler periodogram.
"
From astrophysics to fusion plasmas: signal processing and system optimization analysis for ITER
Dr Duccio Testa, Ecole Polytechnique Fédérale de Lausanne, Switzerland
Abstract
Efficient, real-time and unsupervised data analysis is one of the key elements for achieving scientific success in complex engineering and physical systems, of which three examples are the currently operating Joint European Torus (JET) and the soon-to-be-built International Thermonuclear Experimental Reactor (ITER) and the Square Kilometre Array (SKA) telescope.
There is a wealth of signal processing techniques that are being applied to data analysis in such complex systems, and here we wish to present some examples of the synergies that can be exploited when combining ideas and methods from different fields, such as astronomy and astrophysics and thermonuclear fusion plasmas.
One problem which is common to these subjects is the determination of pulsation modes from irregularly sampled time-series. We have used recent techniques of signal processing in astronomy and astrophysics, based on the Sparse Representations of Signals, to solve current questions arising in thermonuclear fusion plasmas. Two examples are the detection of magneto-hydrodynamic instabilities, which is now performed routinely in JET in real-time on a sub-millisecond time-scale, and the studies leading to the optimization of the magnetic diagnostic system in ITER. These questions have been solved formulating them as inverse problems, despite the fact that these applicative frameworks are extremely different from the classical use of Sparse Representations, on both the theoretical and computational points of view.
Requirements, prospects and ideas for the signal processing and real-time data analysis applications of this method to routine operation of ITER and of the SKA telescope will be discussed.
Finally, we will conclude with an example of a potential application of the Sparse Representation method to the analysis of electrical prospections (using the so-called Schlumberger diagram) in an Etruscan necropolis and in an Etruscan fortress town located close to Rome, both sites dating from around the fifth century BC.
Co-authors:
P Blanchard, A Fasoli, J B Lister, Ecole Polytechnique Fédérale de Lausanne, Switzerland.
S Bourguignon, Institut de Recherche en Communications et Cybernétique, France
H Carfantan, Université de Toulouse, France
A Goodyear, Culham Centre for Fusion Energy, UK
G Vayakis, ITER organization, France
P Blanchard, Ecole Polytechnique Fédérale de Lausanne, Switzerland and JET-EFDA Close Support Unit, Culham Science Centre, UK
A Klein, formerly Massachusetts Institute of Technology, USA.
T Panis, formerly Ecole Polytechnique Fédérale de Lausanne, Switzerland
JET-EFDA contributors, see Appendix of F Romanelli et al, Nuclear Fusion 51 (2011), 094008 Proceedings of the 23rd IAEA Fusion Energy Conference 2010, Daejeon, Korea)
The Gruppo Archeologico Romano, Rome section of the Gruppi Archeologici d’Italia
Show speakers
Dr Duccio Testa, Ecole Polytechnique Fédérale de Lausanne, Switzerland
Dr Duccio Testa, Ecole Polytechnique Fédérale de Lausanne, Switzerland
After finishing high school with A-levels in classical studies, Dr Duccio Testa enrolled in a physics degree at the University of Torino while working as an archaeologist around Torino and Roma. He received the University (bachelor) degree in physics in Torino in July 1994 with a master dissertation on collective phenomena induced by high-energy relativistic electrons.
After teaching in high school and working at the observatory of Pino Torinese for about one year, he began his PhD studies in October 1995 at Imperial College, London (UK), working on the interaction between fast ions and waves in the ion cyclotron and lower hybrid range of frequencies, on experiments performed at the Joint European Torus in Abingdon (UK). He obtained the PhD degree in plasma physics from Imperial College in October 1998. He then held a postdoc position at the Plasma Science and Fusion Centre, Massachusetts Institute of Technology, Boston (USA), from October 1998 to June 2002 and then at the Centre de Recherches en Physique de Plasma, Ecole Polytechnique Fédérale de Lausanne (CH) from July 2002 to June 2005, in both cases working on the Alfvén Eigenmodes Active Diagnostic System at JET.
Since June 2005 he has been a permanent staff of CRRP-EPFL, where he is currently works on the high-frequency magnetic diagnostic system for ITER, on the Alfvén Eigenmodes Active Diagnostic system for JET and on operation of the CRPP Tokamak a Configuration Variable.