8 papers
The Neural Tangent Kernel for Classification
Jonathan Plenk, Sergio Calvo-Ordonez, Alvaro Cartea +3
In wide neural networks, the Neural Tangent Kernel (NTK) remains approximately constant during training, providing a powerful theoretical tool for studying training dynamics, gener…
Doubly Outlier-Robust Online Infinite Hidden Markov Model
Horace Yiu, Leandro Sánchez-Betancourt, Álvaro Cartea +1
We derive a robust update rule for the online infinite hidden Markov model (iHMM) for when the streaming data contains outliers and the model is misspecified. Leveraging recent adv…
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…
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…
Weighted Conditional Flow Matching
Sergio Calvo-Ordonez, Matthieu Meunier, Alvaro Cartea +3
Conditional flow matching (CFM) has emerged as a powerful framework for training continuous normalizing flows due to its computational efficiency and effectiveness. However, standa…
Martingale Posterior Neural Networks for Fast Sequential Decision Making
Gerardo Duran-Martin, Leandro Sánchez-Betancourt, Álvaro Cartea +1
We introduce scalable algorithms for online learning of neural network parameters and Bayesian sequential decision making. Unlike classical Bayesian neural networks, which induce p…
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…
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…