AI RESEARCH
ShakyPrepend: A Multi-Group Learner with Improved Sample Complexity
arXiv CS.LG
•
ArXi:2603.07319v1 Announce Type: new Multi-group learning is a learning task that focuses on controlling predictors' conditional losses over specified subgroups. We propose ShakyPrepend, a method that leverages tools inspired by differential privacy to obtain improved theoretical guarantees over existing approaches. Through numerical experiments, we nstrate that ShakyPrepend adapts to both group structure and spatial heterogeneity. We provide practical guidance for deploying multi-group learning algorithms in real-world settings.