Beyond calibration: estimating the grouping loss of modern neural networks
The ability to ensure that a classifier gives reliable confidence scores is essential to ensure informed decision-making. To this end, recent work has focused on miscalibration, i.e., the over or under confidence of model scores. Yet calibration is not enough: even a perfectly calibrated classifier with the best possible accuracy can have confidence scores that are far from the true posterior probabilities. This is due to the grouping loss, created by samples with the same confidence scores but different true posterior probabilities. Proper scoring rule theory shows that given the calibration loss, the missing piece to characterize individual errors is the grouping loss. While there are many estimators of the calibration loss, none exists for the grouping loss in standard settings. Here, we propose an estimator to approximate the grouping loss. We show that modern neural network architectures in vision and NLP exhibit grouping loss, notably in distribution shifts settings, which highlights the importance of pre-production validation.
Code (2)
Tasks
Decision Makingscoring ruleSimilar Papers 제목 키워드 기반
Reconfidencing LLMs from the Grouping Loss Perspective
Large Language Models (LLMs), including ChatGPT and LLaMA, are susceptible to generating hallucinated answers in a confident tone. While efforts to elicit and calibrate confidence scores have proven useful, recent findin…
Uncertainty QuantificationCalibrating sufficiently
When probabilistic classifiers are trained and calibrated, the so-called grouping loss component of the calibration loss can easily be overlooked. Grouping loss refers to the gap between observable information and inform…
Decision from Suboptimal Classifiers: Excess Risk Pre- and Post-Calibration
Probabilistic classifiers are central for making informed decisions under uncertainty. Based on the maximum expected utility principle, optimal decision rules can be derived using the posterior class probabilities and mi…
Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate Shift
We establish a new model-agnostic optimization framework for out-of-distribution generalization via multicalibration, a criterion that ensures a predictor is calibrated across a family of overlapping groups. Multicalibra…
Out-of-Distribution GeneralizationA Variational Estimator for $L_p$ Calibration Errors
Calibration$\unicode{x2014}$the problem of ensuring that predicted probabilities align with observed class frequencies$\unicode{x2014}$is a basic desideratum for reliable prediction with machine learning systems. Calibra…