57 citations · 139 across the 10 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cond-mat.dis-nn2023★ 4 cited
Stochastic Gradient Descent-like relaxation is equivalent to Metropolis dynamics in discrete optimization and inference problems
Maria Chiara Angelini, Angelo Giorgio Cavaliere, Raffaele Marino +1
Is Stochastic Gradient Descent (SGD) substantially different from Metropolis Monte Carlo dynamics? This is a fundamental question at the time of understanding the most used trainin…
cond-mat.dis-nn2023★ 11 cited
Phase transitions in the mini-batch size for sparse and dense two-layer neural networks
Raffaele Marino, Federico Ricci-Tersenghi
The use of mini-batches of data in training artificial neural networks is nowadays very common. Despite its broad usage, theories explaining quantitatively how large or small the o…