Pith. sign in

REVIEW 2 cited by

Calibrated Forecasts: The Minimax Proof

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2209.05863 v2 pith:6EQC72I5 submitted 2022-09-13 econ.TH cs.GTcs.LGstat.ML

Sergiu Hart This is my paper
classification econ.THcs.GTcs.LGstat.ML
keywords calibratedforecastsminimaxproofcalibrationerrorexistenceformal
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

A formal write-up of the simple proof (1995) of the existence of calibrated forecasts by the minimax theorem, which moreover shows that $N^3$ periods suffice to guarantee a calibration error of at most $1/N$.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. High-Dimensional Calibration from Swap Regret

    cs.LG 2025-05 conditional novelty 7.0 of 10

    TreeCal achieves epsilon-calibration over arbitrary convex sets and norms in (diam/eps)^{O(rho/eps^2)} rounds, and a new lower bound shows exp(poly(1/eps)) rounds are necessary for l1-calibration on the simplex.

  2. Improved and Oracle-Efficient Online $\ell_1$-Multicalibration

    cs.LG 2025-05 accept novelty 6.0 of 10

    For online l1-multicalibration, the paper achieves eO(T^{-1/3}) for finite group families and eO(T^{-1/4}) with an offline oracle, improving prior oracle-efficient rates.

Pith tools