162 citations · 488 across the 53 of their papers we have counts for
3 papers · 1 filter
A new approach to posterior contraction rates via Wasserstein dynamics
Emanuele Dolera, Stefano Favaro, Edoardo Mainini
This paper presents a new approach to the classical problem of quantifying posterior contraction rates (PCRs) in Bayesian statistics. Our approach relies on Wasserstein distance, a…
Doubly infinite residual neural networks: a diffusion process approach
Stefano Peluchetti, Stefano Favaro
Modern neural networks (NN) featuring a large number of layers (depth) and units per layer (width) have achieved a remarkable performance across many domains. While there exists a…
Stable behaviour of infinitely wide deep neural networks
Stefano Favaro, Sandra Fortini, Stefano Peluchetti
We consider fully connected feed-forward deep neural networks (NNs) where weights and biases are independent and identically distributed as symmetric centered stable distributions.…