Optimization is easy and learning is hard in the typical function

Proceedings of the IEEE Conference on Evolutionary Computation, ICEC

Volumn 2, Issue , 2000, Pages 924-931

  English, Thomas M ^a  

^a Tom English Project   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMIC INFORMATION THEORY; ALGORITHMIC INFORMATIONS; FINITE FUNCTIONS; LEARNING ACCURACY; OPTIMIZERS; PARTIAL FUNCTIONS; RANDOM FUNCTIONS; RANDOM SAMPLING;

ALGORITHMS; COMPUTATIONAL COMPLEXITY; LEARNING SYSTEMS; OPTIMIZATION; RANDOM PROCESSES; COMPUTER SCIENCE; EVOLUTIONARY ALGORITHMS;

INFORMATION THEORY; ALGORITHMS;

EID: 0033676164     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. Schaffer, C. 1994. "A conservation law for generalization performance," in Proc. Eleventh lnt'l Conf on Machine Learning, H. Willian and W. Cohen, eds. San Francisco: Morgan Kaufmann, pp. 259-265.
2. Wolpert, D. H., and W. G. Macready. 1997. "No free lunch theorems for optimization," IEEE Trans. Evolutionary Computarion, vol. 1, no. 1, pp. 67-82.
3. English, T. M. 1999. "Some Information Theoretic Results on Evolutionary Optimization," in Proc. Of the 1999 Congress on Evolutionary Computation: CEC99. Piscataway, New Jersey: IEEE Service Center, pp. 788-795.
4. Chaitin, G. J. 1999. The Unknowable, New York: Springer- Verlag, chap. 6.
5. Cover, T. M., and J. A. Thomas. 1991. Elements of Information Theory, New York: Wiley & Sons.
6. Breeden, J. L. 1994. "An EP/GA synthesis for optimal state space representations," in Proc. Third Annual Corf. on Evolutionary Programming, A. Sebald and L. Fogel, eds. River Edge, NF: World Scientific, pp. 216-223.
7. English, T. M. 1996. "Evaluation of evolutionary and genetic optimizers: No free lunch," in Evolutionary Programming V: Proc. Fifth Ann. Conf. on Evolutionary Programming, L. Fogel, P. Angeline, and T. Back, eds. Cambridge, Mass.: MIT Press, pp. 163-169.