Skip to main navigation Skip to search Skip to main content

Extending Temperature Scaling with Homogenizing Maps

Research output: Contribution to journal › Article › peer-review

Abstract

As machine learning models continue to grow more complex, poor calibration significantly limits the reliability of their predictions. Temperature scaling learns a single temperature parameter to scale the output logits, and despite its simplicity, remains one of the most effective post-hoc recalibration methods. We identify one of temperature scaling’s defining attributes, that it increases the uncertainty of the predictions in a manner that we term homogenization, and propose to learn the optimal recalibration mapping from a larger class of functions that satisfies this property. We demonstrate the advantage of our method over temperature scaling in both calibration and out-of-distribution detection. Additionally, we extend our methodology and experimental evaluation to recalibration in the Bayesian setting.

Original languageEnglish (US)
JournalJournal of Machine Learning Research
Volume26
StatePublished - 2025

Keywords

  • entropy
  • out-of-distribution
  • recalibration
  • temperature scaling
  • uncertainty quantification

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Statistics and Probability
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Extending Temperature Scaling with Homogenizing Maps'. Together they form a unique fingerprint.

Cite this