Large Scale Online Learning

We consider situations where training data is abundant and computing resources are comparatively scarce. We argue that suitably designed online learning algorithms asymptotically outperform any batch learning algorithm. Both theoretical and experimental evidences are presented.

• Type: Conference
• Year: 2003
• Where: NIPS
• Authors: Léon Bottou, Yann LeCun
• Keywords: Batch Learning Algorithm, Learning Algorithm, NIPS 2003, NIPS 2007, Online Learning Algorithms