A new conformal framework learns polyhedral uncertainty sets tailored to robust optimization objectives, minimizing decision loss while preserving coverage via calibration and independent re-calibration.
Renukanandan Tumu, Matthew Cleaveland, Rahul Mangharam, George Pappas, and Lars Lindemann
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2roles
background 1polarities
background 1representative citing papers
Systematic benchmarking reveals that regression calibration metrics frequently disagree on recalibration quality, with ENCE and CWC identified as more consistent performers.
citing papers explorer
-
Learning Polyhedral Conformal Sets for Robust Optimization
A new conformal framework learns polyhedral uncertainty sets tailored to robust optimization objectives, minimizing decision loss while preserving coverage via calibration and independent re-calibration.
-
Evaluating the Quality of the Quantified Uncertainty for (Re)Calibration of Data-Driven Regression Models
Systematic benchmarking reveals that regression calibration metrics frequently disagree on recalibration quality, with ENCE and CWC identified as more consistent performers.