手法を比較

	モデルキャリブレーション	ロジスティック回帰
分野	機械学習	研究統計
系統	Machine learning	Process / pipeline
提唱年	2017	1958
提唱者	Platt; Guo et al.	David Roxbee Cox
種類	Post-hoc probability correction technique	Method
原典	Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017). On calibration of modern neural networks. International Conference on Machine Learning, 1321–1330.	Cox, D. R. (1958). The regression analysis of binary sequences. Journal of the Royal Statistical Society, Series B, 20(2), 215–242.
別名	Classifier Calibration, Probability Calibration, Score Calibration, Model Kalibrasyonu	logit model, binomial logistic regression, LR
関連	3	3
概要	Model calibration is a post-hoc technique that adjusts the probability outputs of a trained classifier so that predicted confidence scores match empirical outcome frequencies. A classifier is said to be perfectly calibrated if, among all predictions made with confidence p, exactly a fraction p of them are correct. Systematic miscalibration of modern deep neural networks was rigorously documented by Guo et al. (2017), who showed that networks trained with standard cross-entropy loss tend to be overconfident, and proposed temperature scaling as a simple, effective remedy.	Logistic regression is a statistical method for modeling the probability of a binary outcome (disease present/absent, success/failure) as a function of continuous and categorical predictors. Developed by David Roxbee Cox (1958), it solves the problem of predicting categorical outcomes by applying a logistic transformation to constrain predictions to the [0,1] probability interval, enabling accurate risk stratification, diagnostic prediction, and causal inference in epidemiology, medicine, and social science.