|
This article is cited in 2 scientific papers (total in 2 papers)
Information Theory
New upper bounds in the hypothesis testing problem with information constraints
M. V. Burnashev Kharkevich Institute for Information Transmission Problems,
Russian Academy of Sciences, Moscow, Russia
Abstract:
We consider a hypothesis testing problem where a part of data cannot be observed. Our helper observes the missed data and can send us a limited amount of information about them. What kind of this limited information will allow us to make the best statistical inference? In particular, what is the minimum information sufficient to obtain the same results as if we directly observed all the data? We derive estimates for this minimum information and some other similar results.
Keywords:
hypothesis testing, information constraints, error probabilities.
Received: 10.04.2020 Revised: 15.05.2020 Accepted: 19.05.2020
Citation:
M. V. Burnashev, “New upper bounds in the hypothesis testing problem with information constraints”, Probl. Peredachi Inf., 56:2 (2020), 64–81; Problems Inform. Transmission, 56:2 (2020), 157–172
Linking options:
https://www.mathnet.ru/eng/ppi2316 https://www.mathnet.ru/eng/ppi/v56/i2/p64
|
Statistics & downloads: |
Abstract page: | 132 | Full-text PDF : | 15 | References: | 18 | First page: | 7 |
|