Privacy-Preserving Statistical Learning and Testing
775
16.1
Microsoft Research335 тыс
Следующее
12.09.19 – 3 10244:15Популярные
Опубликовано 12 сентября 2019, 17:52
Identity Testing and Distributional Property Learning are two fundamental problems in statistical inference. However, in many settings, data may contain sensitive information about individuals. It is critical that our methods should protect sensitive information, meanwhile not preclude our overall goals of statistical analysis.
In this talk, I will talk about Differentially Private Identity Testing and Distributional Property Learning. We derive almost-tight sample complexity bounds for both problems. Our upper bounds come from privatizing non-private estimators. As to the lower bound, We establish a general coupling method which we believe can be used to obtain strong lower bounds for other statistical problems under privacy.
See more at microsoft.com/en-us/research/v...
In this talk, I will talk about Differentially Private Identity Testing and Distributional Property Learning. We derive almost-tight sample complexity bounds for both problems. Our upper bounds come from privatizing non-private estimators. As to the lower bound, We establish a general coupling method which we believe can be used to obtain strong lower bounds for other statistical problems under privacy.
See more at microsoft.com/en-us/research/v...
Свежие видео
3 дня – 10 3870:13
7 дней – 6 9310:12
8 дней – 6354:10
9 дней – 1 563 89010:34
10 дней – 2612:19Случайные видео
129 дней – 6581:33
142 дня – 1 466 2241:00
171 день – 10 8530:52
31.01.23 – 10 26222:53
03.09.21 – 34 3496:53
3 дня – 1 2611:15
6 дней – 56455:38
8 дней – 1 9090:36
10 дней – 4055:33
16 дней – 2563:46
17 дней – 9740:13
17 дней – 1 6090:22
