Event Details

Haripriya Harikumar is a Research Fellow at the Centre for AI Fundamentals at the University of Manchester. She specialises in trustworthy and secure AI, with expertise in robustness, privacy, and decision-making under uncertainty.

Title: Robust Bayesian Decision Making under Adversarial Uncertainty

Abstract: Scientific experiments are often designed to maximise information gain, yet in many applications the primary objective is to support reliable downstream decision-making. Existing decision-aware experimental design and active learning methods typically assume well-specified outcome models and implicitly rely on the stability of the optimal decision under real-world perturbations. In practice, however, experimental outcomes are frequently influenced by hidden or weakly modeled effects, which can substantially alter decision optimality and lead to misleading conclusions. We study sequential adversarially robust decision-aware experimental design, where data acquisition has to take into account information gain against plausible worst-case unexpected effects, modeled here as variation in adversarial variables. Building on Bayesian decision theory, we formalize an adversarially robust optimal decision under this setting and derive a principled Bayesian experimental design criterion. The criterion explicitly targets decision stability rather than nominal optimality. Experiments show that conventional decision-aware design can converge rapidly to high-confidence yet fragile decisions, while our robustness-aware approach yields decisions that are significantly more stable and reliable under adversarial variation.

Bio: Haripriya Harikumar is a Research Fellow at the Centre for AI Fundamentals at the University of Manchester. She specialises in trustworthy and secure AI, with expertise in robustness, privacy, and decision-making under uncertainty. This includes designing methods that preserve the privacy of sensitive data and enable reliable predictions and safe decision-making under adversarial threats and distribution shift. She is also deeply interested in the underlying principles of out-of-distribution detection, data manifold learning, machine unlearning and the robustness of Language Vision Models and Large Language Models. She also works on reliable generative and agentic AI for scientific discovery, combining methodological development with applications in healthcare, science, online platforms, and sustainable materials.

Come to the Sky Lounge at 12 o'clock - drinks & refreshments will be provided :)