Gradient Descent with Identity Initialization Efficiently Learns Positive-Definite Linear Transformations by Deep Residual Networks (Q5154121): Difference between revisions
From MaRDI portal
Created a new Item |
ReferenceBot (talk | contribs) Changed an Item |
||
| (7 intermediate revisions by 6 users not shown) | |||
| Property / author | |||
| Property / author: David P. Helmbold / rank | |||
| Property / author | |||
| Property / author: David P. Helmbold / rank | |||
Normal rank | |||
| Property / MaRDI profile type | |||
| Property / MaRDI profile type: MaRDI publication profile / rank | |||
Normal rank | |||
| Property / Wikidata QID | |||
| Property / Wikidata QID: Q91053158 / rank | |||
Normal rank | |||
| Property / OpenAlex ID | |||
| Property / OpenAlex ID: W2911153392 / rank | |||
Normal rank | |||
| Property / arXiv ID | |||
| Property / arXiv ID: 1802.06093 / rank | |||
Normal rank | |||
| Property / cites work | |||
| Property / cites work: Learning Sparse Polynomial Functions / rank | |||
Normal rank | |||
| Property / cites work | |||
| Property / cites work: Q4821526 / rank | |||
Normal rank | |||
| Property / cites work | |||
| Property / cites work: On the Existence and Uniqueness of the Real Logarithm of a Matrix / rank | |||
Normal rank | |||
| Property / cites work | |||
| Property / cites work: Q4360236 / rank | |||
Normal rank | |||
| Property / cites work | |||
| Property / cites work: Q4902474 / rank | |||
Normal rank | |||
| Property / cites work | |||
| Property / cites work: Efficient agnostic learning of neural networks with bounded fan-in / rank | |||
Normal rank | |||
| Property / cites work | |||
| Property / cites work: Hessian Schatten-Norm Regularization for Linear Inverse Problems / rank | |||
Normal rank | |||
| links / mardi / name | links / mardi / name | ||
Latest revision as of 19:03, 26 July 2024
scientific article; zbMATH DE number 7405733
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Gradient Descent with Identity Initialization Efficiently Learns Positive-Definite Linear Transformations by Deep Residual Networks |
scientific article; zbMATH DE number 7405733 |
Statements
Gradient Descent with Identity Initialization Efficiently Learns Positive-Definite Linear Transformations by Deep Residual Networks (English)
0 references
1 October 2021
0 references
