# Algebraic Statistics Seminar

No upcoming events featured at this time...

Mateja Raic - Department of Mathematics, Statistics, and Computer Science, University of Illinois at Chicago

Nov 6, 2018 - 10:00am to 11:00am

College of Science, Applied Mathematics - Seminar - Rettaliata Engineering Center, Room 102

We study networks from a point of view of exponential random graph models. This flexible and versatile statistical family comes equipped with tools to perform inferential statistics, however the standard toolbox assumes large sample sizes and the use of asymptotic theory. In networks, this... read more

Tue.

Nov 6

Christopher O'Neill - Department of Mathematics, University of California at Davis

Apr 26, 2018 - 1:50pm to 3:00pm

College of Science, Applied Mathematics - Seminar - Rettaliata Engineering Center, Room 119

An affine semigroup \(S\) is a subset of \(\mathbb Z_{\geq 0}^k\) that is closed under vector addition, and a factorization of \(a\in S\) is an expression of \(a\) as a sum of generators of \(S\). The delta set of \(a\) is a set of positive integers determined by the ``missing factorization lengths... read more

Thu.

Apr 26

Sonja Petrovic - Department of Applied Mathematics, Illinois Institute of Technology

Apr 25, 2018 - 12:50pm to 1:50pm

College of Science, Applied Mathematics - Seminar - Rettaliata Engineering Center, Room 122

This set of lectures covers some of the basics of how algebraic statistics is used for network modeling. Topics of this lecture include the following: Exponential random graph models. Log-linear models. Sufficient statistics. Example of a small network. Markov bases for conditional tests.

Wed.

Apr 25

Sonja Petrovic - Department of Applied Mathematics, Illinois Institute of Technology

Apr 18, 2018 - 1:50pm to 2:50pm

College of Science, Applied Mathematics - Seminar - Rettaliata Engineering Center, Room 122

This set of lectures covers some of the basics of how algebraic statistics is used for network modeling. We will start by introducing some basic concepts and relevant background. Topics include the following: A statistics primer: introduction to hypothesis test for goodness of fit testing.... read more

Wed.

Apr 18

May 8, 2017 (All day) to May 11, 2017 (All day)

College of Science, Applied Mathematics - Workshop - TBD

The workshop, organized by Alessandro Rinaldo (Carnegie Mellon statistics) and Sonja Petrovic, will honor the legacy that Stephen E. Fienberg left on the field of algebraic statistics for networks. Participation is by invitation.

Mon.

May 8

Annie Raymond, Acting Assistant Professor - Department of Mathematics, University of Washington

Sep 15, 2016 - 2:00pm to 3:00pm

College of Science, Applied Mathematics - Seminar - Rettaliata Engineering, Room 242

The speaker considers the problem of finding sum of squares (sos) expressions to establish the non-negativity of a symmetric polynomial over a discrete hypercube whose coordinates are indexed by k-element subsets of [n]. The speaker develops a variant of the Gatermann-Parrilo symmetry-reduction... read more

Thu.

Sep 15

Sonja Petrovic, Assistant Professor - Department of Applied Mathematics, Illinois Institute of Technology

Sep 6, 2016 - 2:00pm to 3:00pm

Applied Mathematics - Seminar - Rettaliata Engineering, room 242

This talk will discuss the recent comment, written jointly with Vishesh Karwa, on the paper with the same title by Ji and Jin. Ji and Jin collected, cleaned and summarized in various ways citation and coauthorship networks for statisticians. They performed several descriptive analyses of the... read more

Tue.

Sep 6

Todor Markov, Undergraduate Student - IIT

Mar 3, 2016 - 12:45pm

Applied Mathematics - Seminar - RE 103

This talk is meant to connect with earlier seminar discussions on solving polynomial systems via violator spaces and potential applications of that approach.

Thu.

Mar 3

Martin Helmer, Postdoctoral Fellow - Department of Mathematics at the University of California, Berkeley

Feb 25, 2016 - 12:45pm to 1:45pm

Applied Mathematics - Seminar - RE 103

Suppose that we are given a data point u and we wish to approximate this data point by a model X which is parameterized by monomials (this could be a statistical model, a computer vision model, etc.). That is, we wish to find the nearest point to u in our model X, with respect to the (weighted)... read more

Thu.

Feb 25

Jan 28, 2016 - 12:45pm to 1:45pm

Applied Mathematics - Seminar - RE 103

The theory of violator spaces can be used to reduce a large, overdetermined system of polynomial equations to a smaller, more manageable subsystem whose solution set is the same as the original system. We will explore potential applications of this technique for polynomial encodings of graph... read more

Thu.

Jan 28