Close Menu

Events

Mikhail Urusov - Department of Mathematics, University of Duisburg-Essen
Mar 25, 2019 - 1:50pm to 2:55pm
Department of Applied Mathematics - Colloquia - Rettaliata Engineering Center, Room 104
We propose a new algorithm, called EMCEL (Embeddable Markov Chain with Expected time Lag h), for approximating continuous Markov processes in law. The approximation is a discrete-time Markov chain, which in many cases can be constructed explicitly. We prove that the algorithm applies... read more
Mon.
Mar 25
Andreas Sojmark - Mathematical Institute, University of Oxford
Mar 25, 2019 - 3:30pm to 4:30pm
Department of Applied Mathematics - Seminar - Rettaliata Engineering Center, Room 119
TBA
Mon.
Mar 25
Mikhail Urusov - Department of Mathematics, University of Duisburg-Essen
Mar 26, 2019 - 11:25am to 12:45pm
Department of Applied Mathematics - Seminar - Rettaliata Engineering Center, Room 103
We discuss the convergence rates in every p-th Wasserstein distance of the EMCEL and related algorithms. For time marginals, we get the rate of 1/4; on the path space, any rate strictly smaller than 1/4. These rates apply also in irregular situations such as, e.g., an SDE with irregular... read more
Tue.
Mar 26
Ralu Nana Silvia Divan - Staff Scientist, - Center for Nanomaterials, - Argonne National Laboratory
Mar 27, 2019 - 3:15am
Department of Chemistry - Colloquia - PS 111 Auditorium
The promise of nanotechnology will not be realized unless nanometer-scale structures can be precisely and reproducibly fabricated and assembled together into a working nanosystem that can be probed, controlled and manipulated in a reliable manner. The most significant obstacles to the... read more
Wed.
Mar 27
Xiao-Li Meng - Department of Statistics, Harvard University
Apr 1, 2019 - 12:50pm to 1:50pm
Department of Applied Mathematics - Other - Hermann Hall Ballroom
Bias-Variance Tradeoff, also known as the efficiency-robustness tradeoff or relevance-robustness tradeoff, is a principle of “no free lunch” in statistical analysis. Lower random noise (variance) comes with higher systemic error (bias), and vice versa. Through a painful story and a lovely... read more
Mon.
Apr 1
Xiao-Li Meng - Department of Statistics, Harvard University
Apr 1, 2019 - 6:00pm to 7:00pm
Department of Applied Mathematics - Lecture - Hermann Hall Ballroom
The term “Big Data” emphasizes data quantity, not quality. However, many of the current measures of statistical uncertainties and errors are adequate only when the data are of the desired quality, that is, when they can be viewed as probabilistic samples. We show that once we take into... read more
Mon.
Apr 1
Xiao-Li Meng - Department of Statistics, Harvard University
Apr 2, 2019 - 10:00am to 11:00am
Department of Applied Mathematics - Seminar - Rettaliata Engineering Center, Room 124
For years, it irritated me whenever someone calling the EM (expectation-maximization) algorithm an estimation procedure. I’d argue passionately that EM merely is an algorithm designed to compute a maximum likelihood estimator (MLE). Therefore the estimation principle/procedure is MLE, not EM,... read more
Tue.
Apr 2
Zachary Feinstein - McKelvey School of Engineering, Washington University in St. Louis
Apr 2, 2019 - 11:25am to 12:45pm
Department of Applied Mathematics - Seminar - Rettaliata Engineering Center, Room 103
TBA
Tue.
Apr 2
Xiao-Li Meng - Department of Statistics, Harvard University
Apr 2, 2019 - 3:15pm to 4:15pm
Department of Applied Mathematics - Seminar - TBA
This talk is based on Meng (2018, pp 51-57), a contribution to the special issue on ``The Role of Statistics in the Era of Big Data" organized by Statistics and Probability Letters, with the title above and the following abstract: ``Highly Principled Data Science insists on methodologies... read more
Tue.
Apr 2
Jin Ma - Department of Mathematics, University of South California
Apr 8, 2019 - 1:50pm to 2:55pm
Department of Applied Mathematics - Colloquia - Rettaliata Engineering Center, Room 104
TBA
Mon.
Apr 8

Pages