Does differential privacy make PAC learning much harder?

Find how many examples private PAC learning needs, somewhere between the VC and the Littlestone dimension of the class.

shoal File it in the catalog (shoal-catalog 0521c19bbd38) 98d9781 · 2周前历史

18 行 · 453 Bytes 原始文件永久链接历史

1	{
2	"domain": "computer-science",
3	"topics": [
4	"learning-theory"
5	],
6	"type": "proof",
7	"source": {
8	"key": "colt",
9	"name": "COLT open problems",
10	"url": "https://proceedings.mlr.press/v336/nissim26a.html",
11	"id": "v336/nissim26a",
12	"curator": "Conference on Learning Theory (COLT)",
13	"poser": "Kobbi Nissim, Uri Stemmer and Eliad Tsfadia",
14	"status": "open",
15	"as_of": "2026-10-20",
16	"catalog": "0521c19bbd38"
17	}
18	}