93 citations · 245 across the 15 of their papers we have counts for
19 papers
Publicly-Verifiable Certificates for Statistical Algorithms
Michael Ngo, Michael P. Kim
Following Goldwasser, Rothblum, Shafer, and Yehudayoff, who defined a framework for interactive proofs of learning [ITCS'21], we initiate the study of non-interactive proofs of lea…
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…
Swap Agnostic Learning, or Characterizing Omniprediction via Multicalibration
Parikshit Gopalan, Michael P. Kim, Omer Reingold
We introduce and study Swap Agnostic Learning. The problem can be phrased as a game between a predictor and an adversary: first, the predictor selects a hypothesis ; then, the a…
Loss Minimization through the Lens of Outcome Indistinguishability
Parikshit Gopalan, Lunjia Hu, Michael P. Kim +2
We present a new perspective on loss minimization and the recent notion of Omniprediction through the lens of Outcome Indistingusihability. For a collection of losses and hypothesi…
Making Decisions under Outcome Performativity
Michael P. Kim, Juan C. Perdomo
Decision-makers often act in response to data-driven predictions, with the goal of achieving favorable outcomes. In such settings, predictions don't passively forecast the future;…