Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Model Agreement via Anchoring
Eric Eaton, Surbhi Goel, Marcel Hussing +4
Numerous lines of aim to control -- the extent to which two machine learning models disagree in their predictions. We adopt a simple and standard noti…
cs.LG2026
Computationally Efficient Replicable Learning of Parities and Applications
Moshe Noivirt, Jessica Sorrell, Eliad Tsfadia
We study the computational relationship between replicability (Impagliazzo et al. [STOC `22], Ghazi et al. [NeurIPS `21]) and other stability notions. Specifically, we focus on rep…