Parametric Learning and Monte Carlo Optimization

This paper uncovers and explores the close relationship between Monte Carlo Optimization of a parametrized integral (MCO), Parametric machine-Learning (PL), and `blackbox' or `oracle'-based optimization (BO). We make four contributions. First, we prove that MCO is mathematically identical to a broad class of PL problems. This identity potentially provides a new application domain for all broadly applicable PL techniques: MCO. Second, we introduce immediate sampling, a new version of the Probability Collectives (PC) algorithm for blackbox optimization. Immediate sampling transforms the original BO problem into an MCO problem. Accordingly, by combining these first two contributions, we can apply all PL techniques to BO. In our third contribution we validate this way of improving BO by demonstrating that cross-validation and bagging improve immediate sampling. Finally, conventional MC and MCO procedures ignore the relationship between the sample point locations and the associated values of the integrand; only the values of the integrand at those locations are considered. We demonstrate that one can exploit the sample location information using PL techniques, for example by forming a fit of the sample locations to the associated values of the integrand. This provides an additional way to apply PL techniques to improve MCO.

[1]  Donald R. Jones,et al.  Efficient Global Optimization of Expensive Black-Box Functions , 1998, J. Glob. Optim..

[2]  Pedro Larrañaga,et al.  Towards a New Evolutionary Computation - Advances in the Estimation of Distribution Algorithms , 2006, Towards a New Evolutionary Computation.

[3]  Yuri Ermoliev,et al.  Monte Carlo Optimization and Path Dependent Nonstationary Laws of Large Numbers , 1998 .

[4]  Carl E. Rasmussen,et al.  Bayesian Monte Carlo , 2002, NIPS.

[5]  David H. Wolpert,et al.  Discrete, Continuous, and Constrained Optimization Using Collectives , 2004 .

[6]  David H. Wolpert,et al.  Product distribution theory for control of multi-agent systems , 2004, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004..

[7]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[8]  David H. Wolpert,et al.  Information Theory - The Bridge Connecting Bounded Rational Game Theory and Statistical Physics , 2004, ArXiv.

[9]  M. R. Leadbetter,et al.  Extremes and Related Properties of Random Sequences and Processes: Springer Series in Statistics , 1983 .

[10]  D. Wolpert RECONCILING BAYESIAN AND NON-BAYESIAN ANALYSIS , 1996 .

[11]  Philip E. Gill,et al.  Practical optimization , 1981 .

[12]  S. Resnick Extreme Values, Regular Variation, and Point Processes , 1987 .

[13]  Thomas Jansen,et al.  Optimization with randomized search heuristics - the (A)NFL theorem, realistic scenarios, and difficult functions , 2002, Theor. Comput. Sci..

[14]  Paul A. Viola,et al.  MIMIC: Finding Optima by Estimating Probability Densities , 1996, NIPS.

[15]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[16]  Leo Breiman,et al.  Stacked regressions , 2004, Machine Learning.

[17]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[18]  Douglas C. Montgomery,et al.  Response Surface Methodology: Process and Product Optimization Using Designed Experiments , 1995 .

[19]  J. A. Lozano,et al.  Estimation of Distribution Algorithms: A New Tool for Evolutionary Computation , 2001 .

[20]  Padhraic Smyth,et al.  Linearly Combining Density Estimators via Stacking , 1999, Machine Learning.

[21]  David H. Wolpert,et al.  Advances in Distributed Optimization Using Probability Collectives , 2006, Adv. Complex Syst..

[22]  G. Lepage A new algorithm for adaptive multidimensional integration , 1978 .

[23]  David H. Wolpert,et al.  Stacked generalization , 1992, Neural Networks.

[24]  David H. Wolpert,et al.  Adaptive, distributed control of constrained multi-agent systems , 2004, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004..

[25]  Hoon Kim,et al.  Monte Carlo Statistical Methods , 2000, Technometrics.

[26]  V. Vapnik Estimation of Dependences Based on Empirical Data , 2006 .

[27]  J. Berger Statistical Decision Theory and Bayesian Analysis , 1988 .

[28]  H. Sebastian Seung,et al.  Selective Sampling Using the Query by Committee Algorithm , 1997, Machine Learning.

[29]  Marc Toussaint,et al.  A No-Free-Lunch theorem for non-uniform distributions of target functions , 2004, J. Math. Model. Algorithms.

[30]  Vladimir Vapnik,et al.  The Nature of Statistical Learning , 1995 .

[31]  Ilan Kroo,et al.  Fleet Assignment Using Collective Intelligence , 2004 .

[32]  D K Smith,et al.  Numerical Optimization , 2001, J. Oper. Res. Soc..

[33]  Ronald L. Wasserstein,et al.  Monte Carlo: Concepts, Algorithms, and Applications , 1997 .

[34]  Dorothea Heiss-Czedik,et al.  An Introduction to Genetic Algorithms. , 1997, Artificial Life.

[35]  Dirk P. Kroese,et al.  Cross‐Entropy Method , 2011 .

[36]  David H. Wolpert,et al.  Product Distribution Field Theory , 2003, ArXiv.

[37]  David W. Corne,et al.  No Free Lunch and Free Leftovers Theorems for Multiobjective Optimisation Problems , 2003, EMO.

[38]  L. D. Whitley,et al.  The No Free Lunch and problem description length , 2001 .

[39]  David H. Wolpert,et al.  Distributed Constrained Optimization with Semicoordinate Transformations , 2008, ArXiv.

[40]  David H. Wolpert,et al.  No free lunch theorems for optimization , 1997, IEEE Trans. Evol. Comput..

[41]  David H. Wolpert,et al.  On Bias Plus Variance , 1997, Neural Computation.

[42]  David H. Wolpert,et al.  Coevolutionary free lunches , 2005, IEEE Transactions on Evolutionary Computation.

[43]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[44]  David H. Wolpert,et al.  Distributed control by Lagrangian steepest descent , 2004, 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601).

[45]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.