OpenAlex
Wide neural networks of any depth evolve as linear models under gradient descent *
Work
Year: 2020
Type: article
Abstract: A longstanding goal in deep learning research has been to precisely characterize training and generalization. However, the often complex loss landscapes of neural networks have made a theory of learni... more
Cites: 72
Cited by: 397
Related to: 10
FWCI: 52.42
Citation percentile (by year/subfield): 100
Open Access status: green