Search Results for author: Emmanuel Candés

Found 1 papers, 1 papers with code

Overparameterized ReLU Neural Networks Learn the Simplest Models: Neural Isometry and Exact Recovery

1 code implementation30 Sep 2022 Yifei Wang, Yixuan Hua, Emmanuel Candés, Mert Pilanci

For randomly generated data, we show the existence of a phase transition in recovering planted neural network models, which is easy to describe: whenever the ratio between the number of samples and the dimension exceeds a numerical threshold, the recovery succeeds with high probability; otherwise, it fails with high probability.

Cannot find the paper you are looking for? You can Submit a new open access paper.