Our paper "On the Generalization Capabilities of Sharp Minima in Case-Based Reasoning" by Thomas Gabel and Eicke Godehardt has been accepted for oral presentation at this year's International Conference on Case-Based reasoning.

In machine learning and numerical optimization, there has been an ongoing debate about properties of local optima and the impact of these properties on generalization. In this paper, we make a first attempt to address this question for case-based reasoning systems, more specifically for instance-based learning as it takes place in the retain phase. In so doing, we cast case learning as an optimization problem, develop a notion of local optima as well as two greedy algorithms that yield such optima, propose a measure for the flatness or sharpness of these optima and empirically evaluate the relation between sharp minima and the generalization performance of the corresponding learned case base. You can find a draft version of this paper here.