Access the full text.
Sign up today, get DeepDyve free for 14 days.
Loading next page...
/lp/association-for-computing-machinery/evolvability-of-real-functions-hGArE4S8DG
References (22)
-
Varun Kanade, L. Valiant, Jennifer Vaughan (2010)
Evolution with Drifting TargetsArXiv, abs/1005.3566
-
D. Haussler (1992)
Decision Theoretic Generalizations of the PAC Model for Neural Net and Other Learning ApplicationsInf. Comput., 100
-
V. Feldman (2009a)
A complete characterization of statistical query learning with applications to evolvabilityProceedings of the 50th Annual Symposium on Foundations of Computer Science (FOCS’09)
-
Varun Kanade (2011)
Evolution with Recombination2011 IEEE 52nd Annual Symposium on Foundations of Computer Science
-
(2014)
ACM Transactions on Computation Theory -
(2009)
Evolvability. J. ACM -
(2009)
Sex, mixability, and modularity. Proc. Nat. Acad. Sci. 107 -
Adi Livnat, C. Papadimitriou, J. Dushoff, M. Feldman (2008)
A mixability theory for the role of sex in evolutionProceedings of the National Academy of Sciences, 105
-
(1986)
An Algorithmic Theory of Numbers, Graphs, and Convexity. SIAM, Chapter 2. L. Michael. 2012. Evolvability via the Fourier tranform -
K. Ball (1997)
An Elementary Introduction to Modern Convex Geometry -
A. Kalai (2004)
Simulated Annealing for Convex Optimization -
V. Feldman (2009)
A Complete Characterization of Statistical Query Learning with Applications to Evolvability2009 50th Annual IEEE Symposium on Foundations of Computer Science
-
Loizos Michael (2012)
Evolvability via the Fourier transformTheor. Comput. Sci., 462
-
V. Feldman (2011)
Distribution-Independent Evolvability of Linear Threshold FunctionsArXiv, abs/1103.4904
-
V. Feldman (2008)
Evolvability from learning algorithmsProceedings of the fortieth annual ACM symposium on Theory of computing
-
V. Feldman (2009)
Robustness of Evolvability -
M. Kearns (1998)
Efficient noise-tolerant learning from statistical queriesJ. ACM, 25
-
M. Kearns (1993)
Efficient noise-tolerant learning from statistical queriesProceedings of the twenty-fifth annual ACM symposium on Theory of Computing
-
Y. Nesterov, Boris Polyak (2006)
Cubic regularization of Newton method and its global performanceMathematical Programming, 108
-
L. Valiant (2009)
EvolvabilityElectron. Colloquium Comput. Complex., TR06
-
L. Lovász (1986)
Algorithmic theory of numbers, graphs and convexity, 50
-
Adi Livnat, C. Papadimitriou, N. Pippenger, M. Feldman (2010)
Sex, mixability, and modularityProceedings of the National Academy of Sciences, 107
- Publisher
- Association for Computing Machinery
- Copyright
- Copyright © 2014 ACM
- ISSN
- 1942-3454
- eISSN
- 1942-3462
- DOI
- 10.1145/2633598
- Publisher site
- See Article on Publisher Site
Abstract
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. Towards this end, 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 a more general class of metrics.
Journal
ACM Transactions on Computation Theory (TOCT) – Association for Computing Machinery
Published: Jul 1, 2014
Keywords: Evolvability