Particularity
This addresses the problem of designing more effective and responsive adaptive systems for researchers and practitioners in machine learning and AI, though it appears incremental as it builds on existing concepts like lexicase selection.
The paper introduces a design principle for adaptive systems where adaptation is driven by specific environmental challenges rather than aggregated performance measures, tracing its development from genetic programming to broader machine learning applications.
We describe a design principle for adaptive systems under which adaptation is driven by particular challenges that the environment poses, as opposed to average or otherwise aggregated measures of performance over many challenges. We trace the development of this "particularity" approach from the use of lexicase selection in genetic programming to "particularist" approaches to other forms of machine learning and to the design of adaptive systems more generally.