Evolvability

Living organisms function in accordance with complex mechanisms that operate in different ways depending on conditions. Darwin's theory of evolution suggests that such mechanisms evolved through variation guided by natural selection. However, there has existed no theory that would explain quantitatively which mechanisms can so evolve in realistic population sizes within realistic time periods, and which are too complex. In this article, we suggest such a theory. We treat Darwinian evolution as a form of computational learning from examples in which the course of learning is influenced only by the aggregate fitness of the hypotheses on the examples, and not otherwise by specific examples. We formulate a notion of evolvability that distinguishes function classes that are evolvable with polynomially bounded resources from those that are not. We show that in a single stage of evolution monotone Boolean conjunctions and disjunctions are evolvable over the uniform distribution, while Boolean parity functions are not. We suggest that the mechanism that underlies biological evolution overall is “evolvable target pursuit”, which consists of a series of evolutionary stages, each one inexorably pursuing an evolvable target in the technical sense suggested above, each such target being rendered evolvable by the serendipitous combination of the environment and the outcomes of previous evolutionary stages.

[1]  R. Punnett,et al.  The Genetical Theory of Natural Selection , 1930, Nature.

[2]  R. A. Fisher,et al.  The Genetical Theory of Natural Selection , 1931 .

[3]  A. Gray,et al.  I. THE ORIGIN OF SPECIES BY MEANS OF NATURAL SELECTION , 1963 .

[4]  W. Hoeffding.  Probability Inequalities for sums of Bounded Random Variables , 1963 .

[5]  M. Kimura.  Evolutionary Rate at the Molecular Level , 1968, Nature.

[6]  S. Wright.  Evolution And The Genetics Of Populations : A Treatise , 1968 .

[7]  J M Smith,et al.  Evolution and the theory of games , 1976 .

[8]  S. Wright.  Evolution and the Genetics of Populations, Volume 3: Experimental Results and Evolutionary Deductions , 1977 .

[9]  David S. Johnson,et al.  Computers and Intractability: A Guide to the Theory of NP-Completeness , 1978 .

[10]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, STOC '84.

[11]  Leslie G. Valiant,et al.  Computational limitations on learning from examples , 1988, JACM.

[12]  Leslie G. Valiant,et al.  A general lower bound on the number of examples needed for learning , 1988, COLT '88.

[13]  David Haussler,et al.  Learnability and the Vapnik-Chervonenkis dimension , 1989, JACM.

[14]  Manfred K. Warmuth,et al.  Learning integer lattices , 1990, COLT '90.

[15]  Johannes P. Ros.  Learning Boolean Functions with Genetic Algorithms: A PAC Analysis , 1992, FOGA.

[16]  Michael Kearns,et al.  Efficient noise-tolerant learning from statistical queries , 1993, STOC.

[17]  Leslie G. Valiant,et al.  Cryptographic Limitations on Learning Boolean Formulae and Finite Automata , 1993, Machine Learning: From Theory to Applications.

[18]  Umesh V. Vazirani,et al.  An Introduction to Computational Learning Theory , 1994 .

[19]  Jeffrey Horn,et al.  Handbook of evolutionary computation , 1997 .

[20]  J. Drake,et al.  Rates of spontaneous mutation. , 1998, Genetics.

[21]  Leslie G. Valiant,et al.  Robust logics , 1999, STOC '99.

[22]  R. Buerger.  The Mathematical Theory of Selection, Recombination, and Mutation , 2000 .

[23]  Ingo Wegener,et al.  Theoretical Aspects of Evolutionary Algorithms , 2001, ICALP.

[24]  B. Walsh,et al.  Evolutionary Quantitative Genetics , 2019, Handbook of Statistical Genomics.

[25]  Sudhir Kumar,et al.  Mutation rates in mammalian genomes , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[26]  D. Haussler,et al.  Ultraconserved Elements in the Human Genome , 2004, Science.

[27]  Günter P. Wagner,et al.  Complex Adaptations and the Evolution of Evolvability , 2005 .

[28]  A. Reymond,et al.  Conserved non-genic sequences — an unexpected feature of mammalian genomes , 2005, Nature Reviews Genetics.

[29]  Dan Suciu,et al.  Journal of the ACM , 2006 .

[30]  Leslie G. Valiant,et al.  Knowledge Infusion , 2006, AAAI.

[31]  P. Sniegowski,et al.  Evolvability , 2006, Current Biology.

[32]  Vitaly Feldman,et al.  Evolvability from learning algorithms , 2008, STOC.

[33]  Salil P. Vadhan,et al.  Computational Complexity , 2005, Encyclopedia of Cryptography and Security.