Search Results for author:
Found 2 papers, 0 papers with code
Gradient-only line searches: An Alternative to Probabilistic Line Searches
Line searches are capable of adaptively resolving learning rate schedules.
Traversing the noise of dynamic mini-batch sub-sampled loss functions: A visual guide
Mini-batch sub-sampling in neural network training is unavoidable, due to growing data demands, memory-limited computational resources such as graphical processing units (GPUs), and the dynamics of on-line learning.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
