Search Results for author:
Found 3 papers, 0 papers with code
Entropic alternatives to initialization
Local entropic loss functions provide a versatile framework to define architecture-aware regularization procedures.
Partial local entropy and anisotropy in deep weight spaces
We refine a recently-proposed class of local entropic loss functions by restricting the smoothening regularization to only a subset of weights.
Stochastic gradient descent with random learning rate
We propose to optimize neural networks with a uniformly-distributed random learning rate.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
