The Tradeoffs of Large Scale Learning

This contribution develops a theoretical framework that takes into account the effect of approximate optimization on learning algorithms. The analysis shows distinct tradeoffs for the case of small-scale and large-scale learning problems. Small-scale learning problems are subject to the usual approximation–estimation tradeoff. Large-scale learning problems are subject to a qualitatively different tradeoff involving the computational complexity of the underlying optimization algorithms in non-trivial ways. 1 Motivation The computational complexity of learning algorithms has seldom been taken into account by the learning theory. Valiant [1] states that a problem is “learnable” when there exists a probably approximatively correct learning algorithm with polynomial complexity. Whereas much progress has been made on the statistical aspect (e.g., [2, 3, 4]), very little has been told about the complexity side of this proposal (e.g., [5].) Computational complexity becomes the limiting ...

• Type: Conference
• Year: 2007
• Where: NIPS
• Authors: Léon Bottou, Olivier Bousquet
• Keywords: Information Technology, Large-scale Learning Problems, Learning Algorithms, Learning Problems, NIPS 2007