Search Results for author:
Found 2 papers, 0 papers with code
Shallow Univariate ReLu Networks as Splines: Initialization, Loss Surface, Hessian, & Gradient Flow Dynamics
Our implicit regularization results are complementary to recent work arXiv:1906. 07842, done independently, which showed that initialization scale critically controls implicit regularization via a kernel-based argument.
A Functional Characterization of Randomly Initialized Gradient Descent in Deep ReLU Networks
Despite their popularity and successes, deep neural networks are poorly understood theoretically and treated as 'black box' systems.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
