6 papers
Richer Bayesian Last Layers with Subsampled NTK Features
Sergio Calvo-Ordoñez, Jonathan Plenk, Richard Bergna +4
Bayesian Last Layers (BLLs) provide a convenient and computationally efficient way to estimate uncertainty in neural networks. However, they underestimate epistemic uncertainty bec…
Decoupled PFNs: Identifiable Epistemic-Aleatoric Decomposition via Structured Synthetic Priors
Richard Bergna, Stefan Depeweg, José Miguel Hernández-Lobato
Prior-Fitted Networks (PFNs) amortize Bayesian prediction by meta-learning over a synthetic task prior, but their standard output is a posterior predictive distribution over noisy…
A Gaussian Process View on Observation Noise and Initialization in Wide Neural Networks
Sergio Calvo-Ordoñez, Jonathan Plenk, Richard Bergna +4
Performing gradient descent in a wide neural network is equivalent to computing the posterior mean of a Gaussian Process with the Neural Tangent Kernel (NTK-GP), for a specific pri…
Activation-Space Uncertainty Quantification for Pretrained Networks
Richard Bergna, Stefan Depeweg, Sergio Calvo-Ordoñez +3
Reliable uncertainty estimates are crucial for deploying pretrained models; yet, many strong methods for quantifying uncertainty require retraining, Monte Carlo sampling, or expens…
Uncertainty Modeling in Graph Neural Networks via Stochastic Differential Equations
Richard Bergna, Sergio Calvo-Ordoñez, Felix L. Opolka +2
We propose a novel Stochastic Differential Equation (SDE) framework to address the problem of learning uncertainty-aware representations for graph-structured data. While Graph Neur…
Post-Hoc Uncertainty Quantification in Pre-Trained Neural Networks via Activation-Level Gaussian Processes
Richard Bergna, Stefan Depeweg, Sergio Calvo Ordonez +3
Uncertainty quantification in neural networks through methods such as Dropout, Bayesian neural networks and Laplace approximations is either prone to underfitting or computationall…