AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Robust Decision-Making with Partially Calibrated Forecasters

Shayan Kiyani, Hamed Hassani, George J. Pappas, Aaron Roth

ICLR 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Probabilistic calibration

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use the minimax robust policy instead of plug-in best response under the plug-in-tuned adversaryMLP forecaster, squared-loss trained · Bike Sharing (UCI)mean utility: 0.393 -> 0.412Improved
use the robust policy instead of plug-in best response under the plug-in-tuned adversaryMLP forecaster, squared-loss trained · California Housingmean utility: 0.155 -> 0.166Improved
use the robust policy under the robust-tuned adversaryMLP forecaster, squared-loss trained · Bike Sharing (UCI)mean utility: 0.402 -> 0.410Improved
use the robust policy under the robust-tuned adversaryMLP forecaster, squared-loss trained · California Housingmean utility: 0.160 -> 0.164Improved
use the robust policy instead of plug-in best response under i.i.d. evaluationMLP forecaster, squared-loss trained · Bike Sharing (UCI)mean utility: 0.474 -> 0.463Hurt
use the robust policy instead of plug-in best response under i.i.d. evaluationMLP forecaster, squared-loss trained · California Housingmean utility: 0.216 -> 0.207Hurt
require decision calibration (or any stronger calibration) of the forecasterrobust decision rule · theoryoptimality of plug-in best responseImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy