Evolving a Vector Space with any Generating Set

In Valiant’s model of evolution, a class of representations is evolvable iff a polynomialtime process of random mutations guided by selection converges with high probability to a representation as -close as desired from the optimal one, for any required > 0. Several previous positive results exist that can be related to evolving a vector space, but each former result imposes disproportionate representations or restrictions on (re)initialisations, distributions, performance functions and/or the mutator. In this paper, we show that all it takes to evolve a normed vector space is merely a set that generates the space. Furthermore, it takes only Õ(1/ 2) steps and it is essentially stable, agnostic and handles target drifts that rival some proven in fairly restricted settings. Our algorithm can be viewed as a close relative to a popular fifty-years old gradient-free optimization method for which little is still known from the convergence standpoint: Nelder-Mead simplex method. keywords: Evolvability, vector space, Bregman divergence.

[1]  G. Hunanyan,et al.  Portfolio Selection , 2019, Finanzwirtschaft, Banken und Bankmanagement I Finance, Banks and Bank Management.

[2]  Yurii Nesterov,et al.  Random Gradient-Free Minimization of Convex Functions , 2015, Foundations of Computational Mathematics.

[3]  Eörs Szathmáry,et al.  How Can Evolution Learn? - A Reply to Responses. , 2016, Trends in ecology & evolution.

[4]  F. Jordán.  How Can Mature Ecosystems Become Educated? A Response to Watson and Szathmáry. , 2016, Trends in ecology & evolution.

[5]  Adi Livnat,et al.  Evolution and Learning: Used Together, Fused Together. A Response to Watson and Szathmáry. , 2016, Trends in ecology & evolution.

[6]  Evolution and Learning: A Response to Watson and Szathmáry. , 2016, Trends in ecology & evolution.

[7]  Eörs Szathmáry,et al.  How Can Evolution Learn? , 2016, Trends in ecology & evolution.

[8]  Paul Valiant,et al.  Evolvability of Real Functions , 2014, ACM Trans. Comput. Theory.

[9]  Varun Kanade,et al.  Attribute-efficient evolvability of linear functions , 2013, ITCS.

[10]  M. Pekkonen,et al.  Resource Availability and Competition Shape the Evolution of Survival and Growth Ability in a Bacterial Community , 2013, PloS one.

[11]  Loizos Michael.  Evolvability via the Fourier transform , 2012, Theor. Comput. Sci..

[12]  Vitaly Feldman,et al.  Distribution-Independent Evolvability of Linear Threshold Functions , 2011, COLT.

[13]  Frank W. Stearns.  One Hundred Years of Pleiotropy: A Retrospective , 2010, Genetics.

[14]  Leslie G. Valiant,et al.  Evolution with Drifting Targets , 2010, COLT.

[15]  Mark D. Reid,et al.  Composite Binary Losses , 2009, J. Mach. Learn. Res..

[16]  John L. Nazareth,et al.  Introduction to derivative-free optimization , 2010, Math. Comput..

[17]  György Turán,et al.  On Evolvability: The Swapping Algorithm, Product Distributions, and Covariance , 2009, SAGA.

[18]  Vitaly Feldman,et al.  A Complete Characterization of Statistical Query Learning with Applications to Evolvability , 2009, 2009 50th Annual IEEE Symposium on Foundations of Computer Science.

[19]  Ran Kafri,et al.  Genetic Redundancy: New Tricks for Old Genes , 2009, Cell.

[20]  Frank Nielsen,et al.  On the Efficient Minimization of Classification Calibrated Surrogates , 2008, NIPS.

[21]  Inderjit S. Dhillon,et al.  Clustering with Bregman Divergences , 2005, J. Mach. Learn. Res..

[22]  Xin Guo,et al.  On the optimality of conditional expectation as a Bregman predictor , 2005, IEEE Trans. Inf. Theory.

[23]  Shun-ichi Amari,et al.  Methods of information geometry , 2000 .

[24]  J. Hopfield,et al.  From molecular to modular cell biology , 1999, Nature.

[25]  M. Habib.  Probabilistic methods for algorithmic discrete mathematics , 1998 .

[26]  R. C. Merton,et al.  An Analytic Derivation of the Efficient Portfolio Frontier , 1972, Journal of Financial and Quantitative Analysis.

[27]  L. Bregman.  The relaxation method of finding the common point of convex sets and its application to the solution of problems in convex programming , 1967 .

[28]  John A. Nelder,et al.  A Simplex Method for Function Minimization , 1965, Comput. J..

[29]  G. Wagner,et al.  Function and the Evolution of Phenotypic Stability : Connecting Pattern to Process , 2022 .