Search Results for author:
Found 7 papers, 3 papers with code
PAC-Bayes-Chernoff bounds for unbounded losses
This result can be understood as a PAC-Bayesian version of the Cram\'er-Chernoff bound.
If there is no underfitting, there is no Cold Posterior Effect
The cold posterior effect (CPE) (Wenzel et al., 2020) in Bayesian deep learning shows that, for posteriors with a temperature $T<1$, the resulting posterior predictive could have better performances than the Bayesian posterior ($T=1$).
PAC-Chernoff Bounds: Understanding Generalization in the Interpolation Regime
This paper introduces a distribution-dependent PAC-Chernoff bound that exhibits perfect tightness for interpolators, even within over-parameterized model classes.
Variational Linearized Laplace Approximation for Bayesian Deep Learning
Specifically, its training cost is independent of the number of training points.
Correcting Model Bias with Sparse Implicit Processes
Model selection in machine learning (ML) is a crucial part of the Bayesian learning procedure.
Deep Variational Implicit Processes
This generalization is similar to that of deep GPs over GPs, but it is more flexible due to the use of IPs as the prior distribution over the latent functions.
Diversity and Generalization in Neural Network Ensembles
In this work, we combine and expand previously published results in a theoretically sound framework that describes the relationship between diversity and ensemble performance for a wide range of ensemble methods.
