Finite Neural Networks as Mixtures of Gaussian Processes: From Provable Error Bounds to Prior Selection

ArXi:2407.18707v3 Announce Type: replace Infinitely wide or deep neural networks (NNs) with independent and identically distributed (i.i.d.) parameters have been shown to be equivalent to Gaussian processes. Because of the favorable properties of Gaussian processes, this equivalence is commonly employed to analyze neural networks and has led to various breakthroughs over the years.