Showing stat.MLShow all
2 papers · 1 filter
stat.ML2026
Is Multi-Distribution Learning as Easy as PAC Learning: Sharp Rates with Bounded Label Noise
Rafael Hanashiro, Abhishek Shetty, Patrick Jaillet
Towards understanding the statistical complexity of learning from heterogeneous sources, we study the problem of multi-distribution learning. Given data sources, the goal is to…
stat.ML2025
Distribution-Dependent Rates for Multi-Distribution Learning
Rafael Hanashiro, Patrick Jaillet
To address the needs of modeling uncertainty in sensitive machine learning applications, the setup of distributionally robust optimization (DRO) seeks good performance uniformly ac…