2023
DOI: 10.1016/j.acha.2022.08.002
|View full text |Cite
|
Sign up to set email alerts
|

Stable recovery of entangled weights: Towards robust identification of deep neural networks from minimal samples

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

0
11
0

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(11 citation statements)
references
References 29 publications
0
11
0
Order By: Relevance
“…Making these passages rigorous is beyond the scope of this work, and we leave it as an open question. We also highlight that assumption (M3) is common in the related literature [3,22,23,25].…”
Section: Network Model and Main Resultsmentioning
confidence: 70%
See 4 more Smart Citations
“…Making these passages rigorous is beyond the scope of this work, and we leave it as an open question. We also highlight that assumption (M3) is common in the related literature [3,22,23,25].…”
Section: Network Model and Main Resultsmentioning
confidence: 70%
“…This last quantity is provably smaller than the error (22) at initialization, see the discussion after Proposition 1. In the worst case, when all weight errors are aligned, ∆ W,1 is dominated by…”
Section: Network Model and Main Resultsmentioning
confidence: 87%
See 3 more Smart Citations