Search Results for author:
Found 3 papers, 0 papers with code
Stability is Stable: Connections between Replicability, Privacy, and Adaptive Generalization
In particular, we give sample-efficient algorithmic reductions between perfect generalization, approximate differential privacy, and replicability for a broad class of statistical problems.
Reproducibility in Learning
We introduce the notion of a reproducible algorithm in the context of learning.
Boosting in the Presence of Massart Noise
Our upper and lower bounds characterize the complexity of boosting in the distribution-independent PAC model with Massart noise.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
