Privacy-Preserving Statistical Learning and Testing
774
16.1
Microsoft Research334 тыс
Следующее
12.09.19 – 3 08444:15Популярные
130 дней – 1 15259:38
13.02.23 – 3 61757:57Опубликовано 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
17 часов – 8780:53
23 часа – 2990:28
2 дня – 1208:50
4 дня – 2912:52
6 дней – 4646:21
Случайные видео
10.08.23 – 1 9971:14
24.06.23 – 806 1502:19:32
27.12.21 – 7 5090:58
08.02.21 – 271 45113:58
11.11.09 – 4 371 5031:00
12 часов – 189 9941:00
14 часов – 7060:25
14 часов – 1452:22
1 день – 7 4912:05
1 день – 30524:48
11 дней – 59 02124:38
12 дней – 1771:36
15 дней – 1 0430:49
