← Search

Neil K. Chada

2 accepted papers

2025

Decoupling epistemic and aleatoric uncertainties with possibility theory

AISTATS 2025poster

The special role of epistemic uncertainty in Machine Learning is now well recognised, and an increasing amount of research is focused on methods for dealing specifically with such a lack of knowledge. Yet, most often, a probabilistic representation is considered for both aleatoric and epistemic unce…

Cited by 0SourceScholar
2025

Sampling from Bayesian Neural Network Posteriors with Symmetric Minibatch Splitting Langevin Dynamics

AISTATS 2025poster

We propose a scalable kinetic Langevin dynamics algorithm for sampling parameter spaces of big data and AI applications. Our scheme combines a symmetric forward/backward sweep over minibatches with a symmetric discretization of Langevin dynamics. For a particular Langevin splitting method (UBU), we…

Cited by 0SourcecodeScholar