Abstract
The Information-Geometric Optimization (IGO) has been introduced as a unified framework for stochastic search algorithms. Given a parametrized family of probability distributions on the search space, the IGO turns an arbitrary optimization problem on the search space into an optimization problem on the parameter space of the probability distribution family and defines a natural gradient ascent on this space. From the natural gradients defined over the entire parameter space we obtain continuous time trajectories which are the solutions of an ordinary differential equation (ODE). Via discretization, the IGO naturally defines an iterated gradient ascent algorithm. Depending on the chosen distribution family, the IGO recovers several known algorithms such as the pure rank-μ update CMA-ES. Consequently, the continuous time IGO-trajectory can be viewed as an idealization of the original algorithm.
In this paper we study the continuous time trajectories of the IGO given the family of isotropic Gaussian distributions. These trajectories are a deterministic continuous time model of the underlying evolution strategy in the limit for population size to infinity and change rates to zero. On functions that are the composite of a monotone and a convex-quadratic function, we prove the global convergence of the solution of the ODE towards the global optimum. We extend this result to composites of monotone and twice continuously differentiable functions and prove local convergence towards local optima.
Keywords
- Ordinary Differential Equation
- Lyapunov Function
- Global Convergence
- Stochastic Approximation
- Local Convergence
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Auger, A.: Convergence results for the (1, λ)-SA-ES using the theory of ϕ-irreducible Markov chains. Theoretical Computer Science 334(1-3), 35–69 (2005)
Jägersküpper, J.: Probabilistic runtime analysis of (1 + ,λ), ES using isotropic mutations. In: Proceedings of the 2006 Genetic and Evolutionary Computation Conference, GECCO 2006, pp. 461–468. ACM (2006)
Jägersküpper, J.: How the (1 + 1) ES using isotropic mutations minimizes positive definite quadratic forms. Theoretical Computer Science 361(1), 38–56 (2006)
Jägersküpper, J.: Algorithmic analysis of a basic evolutionary algorithm for continuous optimization. Theoretical Computer Science 379(3), 329–347 (2007)
Arnold, L., Auger, A., Hansen, N., Ollivier, Y.: Information-geometric optimization algorithms: a unifying picture via invariance principles. arXiv:1106.3708v1 (2011)
Hansen, N., Muller, S.D., Koumoutsakos, P.: Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (CMA-ES). Evolutionary Computation 11(1), 1–18 (2003)
Baluja, S., Caruana, R.: Removing the genetics from the standard genetic algorithm. In: Proceedings of the 12th International Conference on Machine Learning (1995)
Ostermeier, A., Gawelczyk, A., Hansen, N.: A derandomized approach to self-adaptation of evolution strategies. Evolutionary Computation 2(4), 369–380 (1994)
Glasmachers, T., Schaul, T., Yi, S., Wierstra, D., Schmidhuber, J.: Exponential natural evolution strategies. In: Proceedings of Genetic and Evolutionary Computation Conference, pp. 393–400. ACM (2010)
Yin, G.G., Rudolph, G., Schwefel, H.P.: Establishing connections between evolutionary algorithms and stochastic approximation. Informatica 1, 93–116 (1995)
Yin, G.G., Rudolph, G., Schwefel, H.P.: Analyzing the (1, λ) evolution strategy via stochastic approximation methods. Evolutionary Computation 3(4), 473–489 (1996)
Kushner, H.J., Yin, G.G.: Stochastic approximation and recursive algorithms and applications, 2nd edn. Springer (2003)
Malagò, L., Matteucci, M., Pistone, G.: Towards the geometry of estimation of distribution algorithms based on the exponential family. In: Proceedings of Foundations of Genetic Algorithms (FOGA 2011), pp. 230–242. ACM (2011)
Akimoto, Y., Nagata, Y., Ono, I., Kobayashi, S.: Theoretical foundation for CMA-ES from information geometry perspective. Algorithmica, Online First (2011)
Khalil, H.K.: Nonlinear systems. Prentice-Hall, Inc. (2002)
Borkar, V.S.: Stochastic approximation: a dynamical systems viewpoint. Cambridge University Press (2008)
Bonnabel, S.: Stochastic gradient descent on Riemannian manifolds. arXiv:1111.5280v2 (2011)
Thorisson, H.: Coupling, stationarity, and regeneration. Springer (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Akimoto, Y., Auger, A., Hansen, N. (2012). Convergence of the Continuous Time Trajectories of Isotropic Evolution Strategies on Monotonic \(\mathcal C^2\)-composite Functions. In: Coello, C.A.C., Cutello, V., Deb, K., Forrest, S., Nicosia, G., Pavone, M. (eds) Parallel Problem Solving from Nature - PPSN XII. PPSN 2012. Lecture Notes in Computer Science, vol 7491. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32937-1_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-32937-1_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32936-4
Online ISBN: 978-3-642-32937-1
eBook Packages: Computer ScienceComputer Science (R0)