How much overparameterization does ALS need for tensor decomposition?

Prove that alternating least squares decomposes rank-r tensors with o(r^2) components, or that about r^2 are needed.

shoal File it in the catalog (shoal-catalog 0521c19bbd38) 8168ff1 · 2周前历史

22 行 · 549 Bytes 原始文件永久链接历史

1	{
2	"domain": "computer-science",
3	"topics": [
4	"learning-theory",
5	"algorithms-complexity"
6	],
7	"type": "proof",
8	"also": [
9	"algorithm"
10	],
11	"source": {
12	"key": "colt",
13	"name": "COLT open problems",
14	"url": "https://proceedings.mlr.press/v336/arvanitakis26a.html",
15	"id": "v336/arvanitakis26a",
16	"curator": "Conference on Learning Theory (COLT)",
17	"poser": "Dionysis Arvanitakis, Vaidehi Srinivas and Aravindan Vijayaraghavan",
18	"status": "open",
19	"as_of": "2026-10-20",
20	"catalog": "0521c19bbd38"
21	}
22	}