Hausdorff dimension, heavy tails, and generalization in neural networks
Sign Up to like & getrecommendations! Published in 2020 at "Journal of Statistical Mechanics: Theory and Experiment"
DOI: 10.1088/1742-5468/ac3ae7
Abstract: Despite its success in a wide range of applications, characterizing the generalization properties of stochastic gradient descent (SGD) in non-convex deep learning problems is still an important challenge. While modeling the trajectories of SGD via… read more here.
Keywords: hausdorff dimension; neural networks; heavy tails; generalization ... See more keywords