Uncertainty-Aware Data-Efficient AI: An Information-Theoretic Perspective
By: Osvaldo Simeone, Yaniv Romano
In context-specific applications such as robotics, telecommunications, and healthcare, artificial intelligence systems often face the challenge of limited training data. This scarcity introduces epistemic uncertainty, i.e., reducible uncertainty stemming from incomplete knowledge of the underlying data distribution, which fundamentally limits predictive performance. This review paper examines formal methodologies that address data-limited regimes through two complementary approaches: quantifying epistemic uncertainty and mitigating data scarcity via synthetic data augmentation. We begin by reviewing generalized Bayesian learning frameworks that characterize epistemic uncertainty through generalized posteriors in the model parameter space, as well as ``post-Bayes'' learning frameworks. We continue by presenting information-theoretic generalization bounds that formalize the relationship between training data quantity and predictive uncertainty, providing a theoretical justification for generalized Bayesian learning. Moving beyond methods with asymptotic statistical validity, we survey uncertainty quantification methods that provide finite-sample statistical guarantees, including conformal prediction and conformal risk control. Finally, we examine recent advances in data efficiency by combining limited labeled data with abundant model predictions or synthetic data. Throughout, we take an information-theoretic perspective, highlighting the role of information measures in quantifying the impact of data scarcity.
Similar Papers
Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'
Artificial Intelligence
AI learns to admit when it doesn't know.
A Theory of the Mechanics of Information: Generalization Through Measurement of Uncertainty (Learning is Measuring)
Machine Learning (CS)
Makes computers learn from messy data easily.
Tutorial on the Probabilistic Unification of Estimation Theory, Machine Learning, and Generative AI
Machine Learning (CS)
Helps computers learn from messy, unclear information.