Efficient noise-tolerant learning from statistical queries
Journal of the ACM (JACM)
Simulated Annealing for Convex Optimization
Mathematics of Operations Research
Evolvability from learning algorithms
STOC '08 Proceedings of the fortieth annual ACM symposium on Theory of computing
Journal of the ACM (JACM)
A Complete Characterization of Statistical Query Learning with Applications to Evolvability
FOCS '09 Proceedings of the 2009 50th Annual IEEE Symposium on Foundations of Computer Science
Evolvability via the Fourier transform
Theoretical Computer Science
Evolvability via the Fourier transform
Theoretical Computer Science
Hi-index | 0.00 |
We formulate a notion of evolvability for functions with domain and range that are real-valued vectors, a compelling way of expressing many natural biological processes. We show that linear and fixed-degree polynomial functions are evolvable in the following dually robust sense: There is a single evolution algorithm that for all convex loss functions converges for all distributions. It is possible that such dually robust results can be achieved by simpler and more natural evolution algorithms. In the second part of the paper we introduce a simple and natural algorithm that we call "wide-scale random noise" and prove a corresponding result for the L2 metric. We conjecture that the algorithm works for more general classes of metrics.