AAAI Publications, Workshops at the Twenty-Seventh AAAI Conference on Artificial Intelligence

Font Size: 
Using Machine Learning to Improve Stochastic Optimization
David Wolpert, Dev Rajnarayan

Last modified: 2013-06-29


In many  stochastic optimization algorithms there is a hyperparameter that controls how the next sampling distribution is determined from the current data set of samples of the objective function. This hyperparameter controls the exploration/exploitation trade-off of the next sample. Typically heuristic "rules of thumb" are used to set that hyperparameter, e.g., a pre-fixed annealing schedule. We show how machine learning provides more principled alternatives to (adaptively) set that hyperparameter, and demonstrate that these alternatives can substantially improve optimization performance.


optimization;stochastic optimization;cross-validation;machine learning;cross-entropy method;genetic algorithms;probability collectives;importance sampling;automated annealing

Full Text: PDF