Swap Agnostic Learning, or Characterizing Omniprediction via Multicalibration Apple Machine Learning Research
A recent line of work shows that notions of multigroup fairness imply surprisingly strong notions of omniprediction: loss minimization guarantees that apply not just for a specific loss function, but for any loss belonging to a large family of losses. While prior work has derived… Read More »Swap Agnostic Learning, or Characterizing Omniprediction via Multicalibration Apple Machine Learning Research