115 citations · 1.1k across the 38 of their papers we have counts for
Showing 2020Show all
3 papers · 1 filter
cs.LG2020★ 5 cited
Partial local entropy and anisotropy in deep weight spaces
Daniele Musso
We refine a recently-proposed class of local entropic loss functions by restricting the smoothening regularization to only a subset of weights. The new loss functions are referred…
hep-th2020★ 3 cited
Gapped dilatons in scale invariant superfluids
Riccardo Argurio, Carlos Hoyos, Daniele Musso +1
We study a paradigmatic model in field theory where a global and scale symmetries are jointly and spontaneously broken. At zero density the model has a non-compact flat dire…
cs.LG2020★ 3 cited
Stochastic gradient descent with random learning rate
Daniele Musso
We propose to optimize neural networks with a uniformly-distributed random learning rate. The associated stochastic gradient descent algorithm can be approximated by continuous sto…