[ugrads] Fwd: [Computational-math-and-statistics-seminar] [Computational Mathematics & Statistics Seminar] Tue, Feb 05, 2019
Lulu Kang
lkang2 at iit.edu
Mon Feb 4 13:59:13 CST 2019
Dear Students
I encourage you to attend the following seminar tomorrow at 1:50 pm (RE 103). In this seminar, I will give a talk on how to conduct optimal design on social networks. My collaborator and I are working on some new ideas on this topic. If you are interested in joining on us to work on this exciting area, come to the seminar tomorrow and learn what is about.
Hope to see you there!
----
Lulu Kang
Associate Professor, Applied Mathematics
Illinois Institute of Technology
P: 312-567-5322
M: lkang2 at iit.edu
W: math.iit.edu/~lkang2
---------- Forwarded message ----------
From: Kan Zhang <kzhang23 at hawk.iit.edu>
Date: Feb 1, 2019, 9:19 PM -0600
To: computational-math-and-statistics-seminar at math.iit.edu
Subject: [Computational-math-and-statistics-seminar] [Computational Mathematics & Statistics Seminar] Tue, Feb 05, 2019
> Dear all,
>
> Our first seminar will be held on Tuesday, Feb 05, 1:50 PM - 3:05 PM. The location has not been assigned yet.
>
> Prof. Lulu Kang will give a talk on the following topic.
>
> Title:
> D-optimal Design for Network A/B Testing
>
> Abstract:
> A/B testing refers to the statistical procedure of conducting an experiment to compare two treatments, A and B, applied to different testing subjects. It is widely used by technology companies such as Facebook, LinkedIn, and Netflix, to compare different algorithms, web-designs, and other online products and services. The subjects participating these online A/B testing experiments are users who are connected in different scales of social networks. Two connected subjects are similar in terms of their social behaviors, education and financial background, and other demographic aspects.
> Hence, it is only natural to assume that their reactions to the online products and services are related to their network adjacency. In this paper, we propose to use the conditional auto-regressive model to present the network structure and include the network effects in the estimation and inference of the treatment effect. A D-optimal design criterion is developed based on the proposed model.
> Mixed integer programming formulations are developed to obtain the D-optimal designs. The effectiveness of the proposed method is shown through numerical results with synthetic networks and real social networks.
>
> Best regards,
> Kan Zhang
> _______________________________________________
> Computational-math-and-statistics-seminar mailing list
> Computational-math-and-statistics-seminar at math.iit.edu
> http://math2015.iit.edu/mailman/listinfo/computational-math-and-statistics-seminar
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://math.iit.edu/pipermail/ugrads/attachments/20190204/dc20aafc/attachment.html>
More information about the ugrads
mailing list