Methoden vergleichen

	Regularisierte Online-Lernverfahren	Regularisierte Logistische Regression
Fachgebiet	Maschinelles Lernen	Maschinelles Lernen
Familie	Machine learning	Machine learning
Entstehungsjahr	2007–2013	1996–2005
Urheber	Xiao, L.; Shalev-Shwartz, S.; McMahan, H. B. et al.	Tibshirani, R. (lasso); Hoerl & Kennard (ridge); Zou & Hastie (elastic net)
Typ	Online optimization framework with regularization	Penalized classification model
Wegweisende Quelle	Xiao, L. (2010). Dual Averaging Methods for Regularized Stochastic and Online Optimization. Journal of Machine Learning Research, 11, 2543–2596.	Tibshirani, R. (1996). Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society: Series B, 58(1), 267–288.
Aliasnamen	FTRL, Follow-the-Regularized-Leader, online regularized optimization, regularized dual averaging	penalized logistic regression, L1 logistic regression, L2 logistic regression, elastic net logistic regression
Verwandt	6	5
Zusammenfassung	Regularized online learning extends the online learning paradigm by incorporating a regularization penalty into each weight update, controlling model complexity while processing data one example at a time. Algorithms such as Follow-the-Regularized-Leader (FTRL) and Regularized Dual Averaging (RDA) make this approach practical at scale, enabling sparse, well-calibrated models on streaming data.	Regularized logistic regression extends standard logistic regression by adding an L1 (lasso), L2 (ridge), or elastic net penalty to the log-likelihood, shrinking coefficients toward zero and preventing overfitting. It is the default choice for binary or multinomial classification when you want interpretable, sparse, or stable coefficient estimates in high-dimensional or collinear feature spaces.