10 papers
From Bayes' Rule to Bayes Rules: Optimal Information Processing and Axiomatic Foundations Beyond Probability
Jeremie Houssineau, Badr-Eddine Chérief-Abdellatif
This paper develops principled updating rules for possibilistic inference, where uncertainty about a fixed parameter is represented by a possibility function, the maxitive analogue…
Possibilistic Predictive Uncertainty for Deep Learning
Yao Ni, Jeremie Houssineau, Yew-Soon Ong +1
Deep neural networks achieve impressive results across diverse applications, yet their overconfidence on unseen inputs necessitates reliable epistemic uncertainty modeling. Existin…
Action-Free Offline-to-Online RL via Discretised State Policies
Natinael Solomon Neggatu, Jeremie Houssineau, Giovanni Montana
Most existing offline RL methods presume the availability of action labels within the dataset, but in many practical scenarios, actions may be missing due to privacy, storage, or s…
Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference
Jasraj Singh, Shelvia Wongso, Jeremie Houssineau +1
Variational inference (VI) is a cornerstone of modern Bayesian learning, enabling approximate inference in complex models. However, its formulation depends on expectations and dive…
Possibilistic Instrumental Variable Regression with Potentially Invalid Instruments
Gregor Steiner, Jeremie Houssineau, Mark F. J. Steel
Instrumental variable regression is a common approach for causal inference in the presence of unobserved confounding. However, identifying valid instruments is often difficult in p…
Evaluation-Time Policy Switching for Offline Reinforcement Learning
Natinael Solomon Neggatu, Jeremie Houssineau, Giovanni Montana
Offline reinforcement learning (RL) looks at learning how to optimally solve tasks using a fixed dataset of interactions from the environment. Many off-policy algorithms developed…