Using Machine Learning to Improve Stochastic Optimization

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.