手法を比較

	正則化オンライン学習	オンライン学習
分野	機械学習	機械学習
系統	Machine learning	Machine learning
提唱年	2007–2013	1958–2000s
提唱者	Xiao, L.; Shalev-Shwartz, S.; McMahan, H. B. et al.	Rosenblatt, F.; Littlestone, N.; Shalev-Shwartz, S. (key contributors)
種類	Online optimization framework with regularization	Learning paradigm (sequential model update)
原典	Xiao, L. (2010). Dual Averaging Methods for Regularized Stochastic and Online Optimization. Journal of Machine Learning Research, 11, 2543–2596.	Shalev-Shwartz, S. (2011). Online Learning and Online Convex Optimization. Foundations and Trends in Machine Learning, 4(2), 107–194.
別名	FTRL, Follow-the-Regularized-Leader, online regularized optimization, regularized dual averaging	incremental learning, sequential learning, streaming learning, online machine learning
関連	6	6
概要	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.	Online learning is a machine learning paradigm in which a model is updated incrementally as each new data point arrives, rather than being trained once on a fixed dataset. It is essential when data streams continuously, storage is limited, or the underlying distribution shifts over time. Theoretical performance is measured by cumulative regret relative to the best fixed predictor in hindsight.