Non-parametric methods for the dynamic stochastic block model and the time-dependent graphon

54 mins 15 secs,  788.45 MB,  MPEG-4 Video  640x360,  29.97 fps,  44100 Hz,  1.93 Mbits/sec
Share this media item:
Embed this media item:


About this item
Image inherited from collection
Description: Pensky, M (University of Central Florida)
Wednesday 14th December 2016 - 14:45 to 15:30
 
Created: 2016-12-20 15:01
Collection: Theoretical Foundations for Statistical Network Analysis
Publisher: Isaac Newton Institute
Copyright: Pensky, M
Language: eng (English)
Distribution: World     (downloadable)
Explicit content: No
Aspect Ratio: 16:9
Screencast: No
Bumper: UCS Default
Trailer: UCS Default
 
Abstract: The Dynamic Stochastic Block Model (DSBM) and the dynamic graphon are natural extensions of the, respectively, Stochastic Block Model and the graphon, from the time-independent to the time-dependent setting. The objective of the present talk is estimation of the tensor of the connection probabilities when it is generated by the DSBM and the dynamic graphon. In particular, in the context of the DSBM, under very few simple non-parametric assumptions, we derive a penalized least squares estimator and show that it satisfies an oracle inequality and also attains the minimax lower bounds for the risk. We extend those results to estimation in the context of the dynamic graphon. The estimators are adaptive to the unknown number of blocks in the context of DSBM or of the smoothness of the graphon function. The technique relies on the vectorization of the model and leads to to much simpler mathematical arguments than the ones used previously in the stationary set up. In addition, all our results are non-asymptotic and allow a variety of extensions.
Available Formats
Format Quality Bitrate Size
MPEG-4 Video * 640x360    1.93 Mbits/sec 788.45 MB View Download
WebM 640x360    652.5 kbits/sec 259.34 MB View Download
iPod Video 480x270    522.34 kbits/sec 207.55 MB View Download
MP3 44100 Hz 249.78 kbits/sec 99.34 MB Listen Download
Auto (Allows browser to choose a format it supports)