Evolution with Drifting Targets

We consider the question of the stability of evolutionary algorithms to gradual changes, or drift, in the target concept. We define an algorithm to be resistant to drift if, for some inverse polynomial drift rate in the target function, it converges to accuracy 1 with polynomial resources, and then stays within that accuracy indefinitely, except with probability at any one time. We show that every evolution algorithm, in the sense of Valiant [20], can be converted using the Correlational Query technique of Feldman [9], into such a drift resistant algorithm. For certain evolutionary algorithms, such as for Boolean conjunctions, we give bounds on the rates of drift that they can resist. We develop some new evolution algorithms that are resistant to significant drift. In particular, we give an algorithm for evolving linear separators over the spherically symmetric distribution that is resistant to a drift rate of O( /n), and another algorithm over the more general product normal distribu...

• Type: Journal
• Year: 2010
• Where: CORR
• Authors: Varun Kanade, Leslie G. Valiant, Jennifer Wortman Vaughan
• Keywords: Algorithm, CORR 2010, Drift, Drift Rate, Education