5 papers
Beyond NNGP: Large Deviations and Feature Learning in Bayesian Neural Networks
Katerina Papagiannouli, Dario Trevisan, Giuseppe Pio Zitto
We study wide Bayesian neural networks focusing on the rare but statistically dominant fluctuations that govern posterior concentration, beyond Gaussian-process limits. Large-devia…
Robust Predictive Uncertainty and Double Descent in Contaminated Bayesian Random Features
Michele Caprio, Katerina Papagiannouli, Siu Lun Chau +1
We propose a robust Bayesian formulation of random feature (RF) regression that accounts explicitly for prior and likelihood misspecification via Huber-style contamination sets. St…
Functional Large Deviations for Wide Deep Neural Networks with Gaussian Initialization and Lipschitz Activations
Claudio Macci, Barbara Pacchiarotti, Katerina Papagiannouli +2
We establish a functional large deviation principle for fully connected multi-layer perceptrons with i.i.d. Gaussian weights (LeCun initialization) and general Lipschitz activation…
Structured Matching via Cost-Regularized Unbalanced Optimal Transport
Emanuele Pardini, Katerina Papagiannouli
Unbalanced optimal transport (UOT) provides a flexible way to match or compare nonnegative finite Radon measures. However, UOT requires a predefined ground transport cost, which ma…
Frequentist Coverage of Bayes Posteriors in Nonlinear Inverse Problems with Gaussian Priors
Youngsoo Baek, Katerina Papagiannouli
We study asymptotic frequentist coverage and approximately Gaussian properties of Bayes posterior credible sets in nonlinear inverse problems when a Gaussian prior is placed on the…