BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//MIT Center for Statistics - ECPv4.6//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:MIT Center for Statistics
X-ORIGINAL-URL:https://stat.mit.edu
X-WR-CALDESC:Events for MIT Center for Statistics
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20171027T110000
DTEND;TZID=America/New_York:20171027T120000
DTSTAMP:20171023T190134
CREATED:20170801T015205Z
LAST-MODIFIED:20171006T204555Z
UID:1683-1509102000-1509105600@stat.mit.edu
SUMMARY:On Learning Theory and Neural Networks
DESCRIPTION:Abstract: \nCan learning theory\, as we know it today\, form a theoretical basis for neural networks. I will try to discuss this question in light of two new results — one positive and one negative. \nBased on joint work with Roy Frostig\, Vineet Gupta and Yoram Singer\, and with Vitaly Feldman \nBiography: \nAmit Daniely is an Assistant Professor at the Hebrew University in Jerusalem\, and a research scientist at Google Research\, Tel-Aviv. Prior to that\, he was a research scientist at Google Research\, Mountain-View. Even prior to that\, he was a Ph.D. student at the Hebrew University of Jerusalem\, Israel\, supervised by Nati Linial and Shai Shalev-Shwartz. His main research interest is Machine Learning Theory. \n \n
URL:https://stat.mit.edu/calendar/stochastics-and-statistic-seminar-amit-daniely/
CATEGORIES:Stochastics and Statistics Seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20171101T110000
DTEND;TZID=America/New_York:20171101T120000
DTSTAMP:20171023T190134
CREATED:20171017T135508Z
LAST-MODIFIED:20171017T142419Z
UID:2113-1509534000-1509537600@stat.mit.edu
SUMMARY:Unbiased Markov chain Monte Carlo with couplings
DESCRIPTION: Abstract: Markov chain Monte Carlo methods provide consistent approximations of integrals as the number of iterations goes to infinity. However\, these estimators are generally biased after any fixed number of iterations\, which complicates both parallel computation. In this talk I will explain how to remove this burn-in bias by using couplings of Markov chains and a telescopic sum argument\, inspired by Glynn & Rhee (2014). The resulting unbiased estimators can be computed independently in parallel\, and averaged. I will present coupling constructions for Metropolis-Hastings\, Gibbs and Hamiltonian Monte Carlo. The proposed methodology will be illustrated on various examples. If time permits\, I will describe how the proposed estimators can approximate the “cut” distribution that arises in Bayesian inference for misspecified models made of sub-models. \nThis is joint work with John O’Leary\, Yves F. Atchade and Jeremy Heng\,\navailable at arxiv.org/abs/1708.03625 and arxiv.org/abs/1709.00404. \n Biography: Pierre Jacob is an Assistant Professor of Statistics at Harvard University since 2015. Pierre was before a postdoctoral research fellow at the University of Oxford and the National University of Singapore. His Ph.D. was from Université Paris-Dauphine on computational methods for Bayesian inference. His current research is on algorithms amenable to parallel computing for Bayesian inference and model comparison\, with a focus on time series models. \nPierre E. Jacob\nAssistant Professor of Statistics\, Harvard University\npersonal website: sites.google.com/site/pierrejacob/\nblog: statisfaction.wordpress.com/ \n
URL:https://stat.mit.edu/calendar/unbiased-markov-chain-monte-carlo-couplings/
CATEGORIES:Stochastics and Statistics Seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20171103T110000
DTEND;TZID=America/New_York:20171103T120000
DTSTAMP:20171023T190134
CREATED:20170801T015205Z
LAST-MODIFIED:20171013T220324Z
UID:1684-1509706800-1509710400@stat.mit.edu
SUMMARY:Statistics\, Computation and Learning with Graph Neural Networks
DESCRIPTION: Abstract: \nDeep Learning\, thanks mostly to Convolutional architectures\, has recently transformed computer vision and speech recognition. Their ability to encode geometric stability priors\, while offering enough expressive power\, is at the core of their success. In such settings\, geometric stability is expressed in terms of local deformations\, and it is enforced thanks to localized convolutional operators that separate the estimation into scales. \nMany problems across applied sciences\, from particle physics to recommender systems\, are formulated in terms of signals defined over non-Euclidean geometries\, and also come with strong geometric stability priors. In this talk\, I will present techniques that exploit geometric stability in general geometries with appropriate graph neural network architectures. We will show that these techniques can all be framed in terms of local graph generators such as the graph Laplacian. We will present some stability certificates\, as well as applications to computer graphics\, particle physics and graph estimation problems. In particular\, we will describe how graph neural networks can be used to reach statistical detection thresholds in community detection on random graph families\, and attack hard combinatorial optimization problems\, such as the Quadratic Assignment Problem. \n Biography: \nJoan Bruna graduated from Universitat Politecnica de Catalunya (Barcelona\, Spain) in both Mathematics and Electrical Engineering. He obtained an M.Sc. in applied mathematics from ENS Cachan (France). He then became a research engineer in an image processing startup\, developing real-time video processing algorithms. He obtained his PhD in Applied Mathematics at Ecole Polytechnique (France). He was a postdoctoral researcher at the Courant Institute\, NYU\, New York\, and a fellow at Facebook AI Research. In 2015\, he became Assistant Professor at UC Berkeley\, Statistics Department\, and starting Fall 2016 he joined the Courant Institute (NYU\, New York) as Assistant Professor in Computer Science\, Data Science and Mathematics (affiliated). His research interests include invariant signal representations\, high-dimensional statistics and stochastic processes\, deep learning and its applications to signal processing. \n
URL:https://stat.mit.edu/calendar/stochastics-and-statistic-seminar-joan-bruna-estrach/
CATEGORIES:Stochastics and Statistics Seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20171117T110000
DTEND;TZID=America/New_York:20171117T120000
DTSTAMP:20171023T190134
CREATED:20170801T015205Z
LAST-MODIFIED:20171002T195128Z
UID:1685-1510916400-1510920000@stat.mit.edu
SUMMARY:Stochastics and Statistics Seminar
DESCRIPTION:
URL:https://stat.mit.edu/calendar/stochastics-and-statistic-seminar-alex-dimakis/
CATEGORIES:Stochastics and Statistics Seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20171201T110000
DTEND;TZID=America/New_York:20171201T120000
DTSTAMP:20171023T190134
CREATED:20170801T015205Z
LAST-MODIFIED:20171006T210007Z
UID:1686-1512126000-1512129600@stat.mit.edu
SUMMARY:Challenges in Developing Learning Algorithms to Personalize Treatment in Real Time
DESCRIPTION:Abstract: \nA formidable challenge in designing sequential treatments is to determine when and in which context it is best to deliver treatments. Consider treatment for individuals struggling with chronic health conditions. Operationally designing the sequential treatments involves the construction of decision rules that input current context of an individual and output a recommended treatment. That is\, the treatment is adapted to the individual’s context; the context may include current health status\, current level of social support and current level of adherence for example. Data sets on individuals with records of time-varying context and treatment delivery can be used to inform the construction of the decision rules. There is much interest in personalizing the decision rules\, particularly in real time as the individual experiences sequences of treatment. Here we discuss our work in designing online “bandit” learning algorithms for use in personalizing mobile health interventions. \nBiography: \nSusan A. Murphy is Professor of Statistics\, Radcliffe Alumnae Professor at the Radcliffe Institute and Professor of Computer Science at the Harvard John A. Paulson School of Engineering and Applied Sciences\, all at Harvard University. Her lab focuses on improving sequential\, individualized\, decision making in health\, in particular on clinical trial design and data analysis to inform the development of just-in-time adaptive interventions in mobile health. The lab’s work is funded by National Institute on Drug Abuse \, by National Institute on Alcohol Abuse and Alcoholism\, by National Heart\, Lung and Blood Institute and by National Institute of Biomedical Imaging and Bioengineering. Susan is a Fellow of the Institute of Mathematical Statistics\, a Fellow of the College on Problems in Drug Dependence\, a former editor of the Annals of Statistics\, a member of the US National Academy of Sciences\, a member of the US National Academy of Medicine and a 2013 MacArthur Fellow. \n
URL:https://stat.mit.edu/calendar/stochastics-and-statistic-seminar-susan-murphy/
CATEGORIES:Stochastics and Statistics Seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20171208T110000
DTEND;TZID=America/New_York:20171208T120000
DTSTAMP:20171023T190134
CREATED:20170801T015205Z
LAST-MODIFIED:20170920T184958Z
UID:1687-1512730800-1512734400@stat.mit.edu
SUMMARY:Stochastics and Statistics Seminar
DESCRIPTION:
URL:https://stat.mit.edu/calendar/stochastics-and-statistics-seminar-alex-bloemendal/
CATEGORIES:Stochastics and Statistics Seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20180420T080000
DTEND;TZID=America/New_York:20180420T170000
DTSTAMP:20171023T190134
CREATED:20170803T135349Z
LAST-MODIFIED:20170830T164525Z
UID:1786-1524211200-1524243600@stat.mit.edu
SUMMARY:SDSCon 2018: Statistics and Data Science Center Conference
DESCRIPTION:More information will be coming soon… \n
URL:https://stat.mit.edu/calendar/sdscon-statistics-data-science-center-conference/
CATEGORIES:SDSC Special Events
END:VEVENT
END:VCALENDAR