5 papers
Optimal Recalibration of an Online Predictor
Lunjia Hu, Kevin Tian, Chutong Yang
We study the problem of recalibrating an online predictor [KE17, OKS24]: given an arbitrary "hint" sequence of forecasts, the learner must output new predictions that are calibrate…
Generalized and Unified Equivalences between Hardness and Pseudoentropy
Lunjia Hu, Salil Vadhan
Pseudoentropy characterizations give quantitatively precise formulations of the relationship between computational hardness and computational randomness. We prove a unified pseudoe…
Simultaneous Blackwell Approachability and Applications to Multiclass Omniprediction
Lunjia Hu, Kevin Tian, Chutong Yang
Omniprediction is a learning problem that requires suboptimality bounds for each of a family of losses against a family of comparator predictors . We ini…
Efficient Swap Multicalibration of Elicitable Properties
Lunjia Hu, Haipeng Luo, Spandan Senapati +1
Multicalibration [HJKRR18] is an algorithmic fairness perspective that demands that the predictions of a predictor are correct conditional on themselves and membership in a collect…
Omnipredicting Single-Index Models with Multi-Index Models
Lunjia Hu, Kevin Tian, Chutong Yang
Recent work on supervised learning [GKR+22] defined the notion of omnipredictors, i.e., predictor functions over features that are simultaneously competitive for minimizing a f…