activity
20242026
collaborators

6 papers

cs.LG2026

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…

cs.LG2026

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…

stat.ML2025

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…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2024

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…