6 papers
Fast Rates for Swap-Agnostic Learning of Proper Losses
Princewill Okoroafor
Swap-agnostic learning strengthens classical agnostic learning by allowing the comparator to select a different hypothesis on each level set of the learner's predictions. This benc…
Oracle-efficient Hybrid Learning with Constrained Adversaries
Princewill Okoroafor, Robert Kleinberg, Michael P. Kim
The Hybrid Online Learning Problem, where features are drawn i.i.d. from an unknown distribution but labels are generated adversarially, is a well-motivated setting positioned betw…
Near-Optimal Algorithms for Omniprediction
Princewill Okoroafor, Robert Kleinberg, Michael P. Kim
Omnipredictors are simple prediction functions that encode loss-minimizing predictions with respect to a hypothesis class , simultaneously for every loss function within a class…
Contextual Dynamic Pricing with Heterogeneous Buyers
Thodoris Lykouris, Sloan Nietert, Princewill Okoroafor +2
We initiate the study of contextual dynamic pricing with a heterogeneous population of buyers, where a seller repeatedly posts prices (over rounds) that depend on the observabl…
Full Swap Regret and Discretized Calibration
Maxwell Fishelson, Robert Kleinberg, Princewill Okoroafor +3
We study the problem of minimizing swap regret in structured normal-form games. Players have a very large (potentially infinite) number of pure actions, but each action has an embe…
Breaking the Barrier for Sequential Calibration
Yuval Dagan, Constantinos Daskalakis, Maxwell Fishelson +3
A set of probabilistic forecasts is calibrated if each prediction of the forecaster closely approximates the empirical distribution of outcomes on the subset of timesteps where tha…