• This event has passed.

Strong data processing inequalities and information percolation

September 20, 2018 @ 4:00 pm - 5:00 pm

Yury Polyanskiy (MIT)

32-D677

Title: Strong data processing inequalities and information percolation
Abstract:  The data-processing inequality, that is, $I(U;Y) \le I(U;X)$ for a Markov chain $U \to X \to Y$, has been the method of choice for proving impossibility (converse) results in information theory and many other disciplines. A channel-dependent improvement is called the strong data-processing inequality (or SDPI). In this talk we will: a) review SDPIs; b) show how point-to-point SDPIs can be combined into an SDPI for a network; c) show recent applications to problems of statistical inference on graphs (spiked Wigner model, community detection etc.)

Details

Date:
September 20, 2018
Time:
4:00 pm - 5:00 pm
Event Category:
Website:
http://stellar.mit.edu/S/project/infoandinf/

32-D677

Other

Speaker Name(s)
Yury Polyanskiy (MIT)
speaker URL
http://people.lids.mit.edu/yp/homepage/

© MIT Statistics + Data Science Center | 77 Massachusetts Avenue | Cambridge, MA 02139-4307 | 617-253-1764 |

Accessibility