A learning-based mathematical programming formulation for the automatic configuration of optimization solvers
This addresses the challenge of solver configuration for optimization practitioners, but it is incremental as it builds on existing machine learning and optimization techniques.
The paper tackles the problem of automatically configuring optimization solvers for specific instances by proposing a methodology that learns a performance function from solved instances and formulates a mixed-integer nonlinear program to select the best configuration, resulting in an efficient approach using off-the-shelf tools.
We propose a methodology, based on machine learning and optimization, for selecting a solver configuration for a given instance. First, we employ a set of solved instances and configurations in order to learn a performance function of the solver. Secondly, we formulate a mixed-integer nonlinear program where the objective/constraints explicitly encode the learnt information, and which we solve, upon the arrival of an unknown instance, to find the best solver configuration for that instance, based on the performance function. The main novelty of our approach lies in the fact that the configuration set search problem is formulated as a mathematical program, which allows us to a) enforce hard dependence and compatibility constraints on the configurations, and b) solve it efficiently with off-the-shelf optimization tools.