方法对比

	在线朴素贝叶斯	在线逻辑回归
领域	机器学习	机器学习
方法族	Machine learning	Machine learning
起源年份	2000s	1960s (perceptron); formalized for logistic loss ~2000s
提出者	Adapted from traditional Naive Bayes; incremental form established by the data-stream mining community (Domingos, Hulten, and others, circa 2000)	Rosenblatt, F. / Widrow, B. (perceptron era); modern SGD form: Bottou, L.
类型	Probabilistic classifier (online/incremental)	Incremental supervised classifier
开创性文献	Domingos, P. & Hulten, G. (2000). Mining high-speed data streams. Proceedings of the 6th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 71–80. ACM.	Bottou, L. (2010). Large-Scale Machine Learning with Stochastic Gradient Descent. In Proceedings of COMPSTAT 2010, 177–186. Physica-Verlag.
别名	Incremental Naive Bayes, Streaming Naive Bayes, Naive Bayes with partial_fit, Online NB	incremental logistic regression, streaming logistic regression, SGD logistic classifier, online binary classifier
相关	6	5
摘要	Online Naive Bayes is an incremental adaptation of the classical Naive Bayes classifier that updates its class-conditional statistics one observation (or one mini-batch) at a time, making it well suited to data streams, very large datasets that cannot be held in memory, and settings where the model must adapt continuously as new labeled examples arrive.	Online Logistic Regression fits a logistic classifier one sample (or mini-batch) at a time via stochastic gradient descent, updating model weights as each observation arrives rather than waiting to see the full dataset. This makes it the standard choice for high-volume, streaming, or memory-constrained binary classification problems where batch training is infeasible.