9 papers
Robust Counterfactual Policy Optimisation via Nondeterministic Causal Models
Jessica Lally, Milad Kazemi, Nicola Paoletti +2
Counterfactual inference approaches for sequential decision-making typically assume deterministic causal models, where all randomness stems from latent variables. However, Markov D…
Robust Counterfactual Inference in Markov Decision Processes
Jessica Lally, Milad Kazemi, Nicola Paoletti
This paper addresses a key limitation in existing counterfactual inference methods for Markov Decision Processes (MDPs). Current approaches assume a specific causal model to make c…
Physics-Informed Neural Operators for Cardiac Electrophysiology
Hannah Lydon, Milad Kazemi, Martin Bishop +1
Accurately simulating systems governed by PDEs, such as voltage fields in cardiac electrophysiology (EP) modelling, remains a significant modelling challenge. Traditional numerical…
Calibrate-Then-Delegate: Safety Monitoring with Risk and Budget Guarantees via Model Cascades
Edoardo Pona, Milad Kazemi, Mehran Hosseini +4
Monitoring LLM safety at scale requires balancing cost and accuracy: a cheap latent-space probe can screen every input, but hard cases should be escalated to a more expensive exper…
Average Reward Reinforcement Learning for Omega-Regular and Mean-Payoff Objectives
Milad Kazemi, Mateo Perez, Fabio Somenzi +3
Recent advances in reinforcement learning (RL) have renewed interest in reward design for shaping agent behavior, but manually crafting reward functions is tedious and error-prone.…
CONFEX: Uncertainty-Aware Counterfactual Explanations with Conformal Guarantees
Aman Bilkhoo, Mehran Hosseini, Milad Kazemi +1
Counterfactual explanations (CFXs) provide human-understandable justifications for model predictions, enabling actionable recourse and enhancing interpretability. To be reliable, C…