Corpus ID: 11796655

Evolution with Drifting Targets

@article{Kanade2010EvolutionWD,
  title={Evolution with Drifting Targets},
  author={Varun Kanade and L. Valiant and Jennifer Wortman Vaughan},
  journal={ArXiv},
  year={2010},
  volume={abs/1005.3566}
}
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 − ǫ with polynomial resources, and then stays within that accuracy indefinitely, except with probability ǫ at any one time. We show that every evolution algorithm, in the sense of Valiant [20], can be converted using the Correlational… Expand
27 Citations
Attribute-efficient evolvability of linear functions
  • 9
  • PDF
Evolving a Vector Space with any Generating Set
  • Highly Influenced
Distribution-free Evolvability of Vector Spaces: All it takes is a Generating Set
  • Highly Influenced
  • PDF
On the Evolvability of Monotone Conjunctions with an Evolutionary Mutation Mechanism
  • Highly Influenced
Evolution with Recombination
  • Varun Kanade
  • Mathematics, Computer Science
  • 2011 IEEE 52nd Annual Symposium on Foundations of Computer Science
  • 2011
  • 39
  • PDF
Distribution-Independent Evolvability of Linear Threshold Functions
  • 22
  • Highly Influenced
  • PDF
Statistical Query Learning (1993; Kearns)
  • 1
  • PDF
Statistical Active Learning Algorithms for Noise Tolerance and Differential Privacy
  • 13
  • PDF
A Complete Characterization of Statistical Query Learning with Applications to Evolvability
  • V. Feldman
  • Computer Science, Mathematics
  • 2009 50th Annual IEEE Symposium on Foundations of Computer Science
  • 2009
  • 50
  • Highly Influenced
  • PDF
...
1
2
3
...

References

SHOWING 1-10 OF 22 REFERENCES
Evolvability from learning algorithms
  • 68
  • Highly Influential
  • PDF
On the complexity of learning from drifting distributions
  • 19
Tracking drifting concepts by minimizing disagreements
  • 114
  • PDF
On Evolvability: The Swapping Algorithm, Product Distributions, and Covariance
  • 15
  • PDF
Efficient noise-tolerant learning from statistical queries
  • 688
  • PDF
Learning with a slowly changing distribution
  • 52
Specification and simulation of statistical query algorithms for efficiency and noise tolerance
  • 42
On Using Extended Statistical Queries to Avoid Membership Queries
  • 45
  • Highly Influential
A Complete Characterization of Statistical Query Learning with Applications to Evolvability
  • V. Feldman
  • Computer Science, Mathematics
  • 2009 50th Annual IEEE Symposium on Foundations of Computer Science
  • 2009
  • 50
  • PDF
Robustness of Evolvability
  • 32
  • Highly Influential
  • PDF
...
1
2
3
...