Showing 2024Show all
3 papers · 1 filter
cs.LG2024
When is Multicalibration Post-Processing Necessary?
Dutch Hansen, Siddartha Devic, Preetum Nakkiran +1
Calibration is a well-studied property of predictors which guarantees meaningful uncertainty estimates. Multicalibration is a related notion -- originating in algorithmic fairness…
cs.LG2024
Transductive Learning Is Compact
Julian Asilis, Siddartha Devic, Shaddin Dughmi +2
We demonstrate a compactness result holding broadly across supervised learning with a general class of loss functions: Any hypothesis class is learnable with transductive sampl…
cs.LG2024
Regularization and Optimal Multiclass Learning
Julian Asilis, Siddartha Devic, Shaddin Dughmi +2
The quintessential learning algorithm of empirical risk minimization (ERM) is known to fail in various settings for which uniform convergence does not characterize learning. It is…