41 citations · 43 across the 6 of their papers we have counts for
3 papers · 1 filter
Learning to Embed Distributions via Maximum Kernel Entropy
Oleksii Kachaiev, Stefano Recanatesi
Empirical data can often be considered as samples from a set of probability distributions. Kernel methods have emerged as a natural approach for learning to classify these distribu…
A simple connection from loss flatness to compressed neural representations
Shirui Chen, Stefano Recanatesi, Eric Shea-Brown
Despite extensive study, the significance of sharpness -- the trace of the loss Hessian at local minima -- remains unclear. We investigate an alternative perspective: how sharpness…
Dimensionality compression and expansion in Deep Neural Networks
Stefano Recanatesi, Matthew Farrell, Madhu Advani +3
Datasets such as images, text, or movies are embedded in high-dimensional spaces. However, in important cases such as images of objects, the statistical structure in the data const…