A Complete Characterization of Statistical Query Learning with Applications to Evolvability

Details A Complete Characterization of Statistical Query Learning with Applications to Evolvability A Complete Characterization of Statistical Query Learning with Applications to Evolvability

2010-02-16

arxiv.org/abs/1002.3183v2

Proceedings of the 44th IEEE Symposium on Foundations of Computer Science, pp 375-384, 2009

Computer Science

Computational Complexity

Scientific paper

Statistical query (SQ) learning model of Kearns (1993) is a natural restriction of the PAC learning model in which a learning algorithm is allowed to obtain estimates of statistical properties of the examples but cannot see the examples themselves. We describe a new and simple characterization of the query complexity of learning in the SQ learning model. Unlike the previously known bounds on SQ learning our characterization preserves the accuracy and the efficiency of learning. The preservation of accuracy implies that that our characterization gives the first characterization of SQ learning in the agnostic learning framework. The preservation of efficiency is achieved using a new boosting technique and allows us to derive a new approach to the design of evolutionary algorithms in Valiant's (2006) model of evolvability. We use this approach to demonstrate the existence of a large class of monotone evolutionary learning algorithms based on square loss performance estimation. These results differ significantly from the few known evolutionary algorithms and give evidence that evolvability in Valiant's model is a more versatile phenomenon than there had been previous reason to suspect.

Affiliated with

Also associated with

No associations

Rating

A Complete Characterization of Statistical Query Learning with Applications to Evolvability does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with A Complete Characterization of Statistical Query Learning with Applications to Evolvability, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A Complete Characterization of Statistical Query Learning with Applications to Evolvability will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-51395