Multi-fidelity optimization method with Asynchronous Generalized Island Model for AutoML

AutoML frameworks seek to find the best configurations of machine learning techniques. A research field that has gained a great deal of popularity in recent years is the combined algorithm selection and hyperparameter optimisation (CASH) problem. Several bio-inspired optimization techniques have been applied in AutoML, each with their drawbacks and benefits. For instance, methods may get stuck evaluating computationally expensive models, or certain solutions may dominate early on and inhibit the discovery of better ones. We propose to use multiple bio-inspired techniques in parallel in a generalized island model & combine this with multi-fidelity optimization to speed up the search. We analyze 3 different island topologies, including fully connected, unconnected, and ring topologies, to understand the trade-offs between information sharing and maintaining diversity. With respect to convergence time, the proposed method outperforms Asynchronous Evolutionary Algorithms and Asynchronous Successive Halving techniques. In an objective comparison based on the OpenML AutoML Benchmark, we also find that the proposed method is competitive with current state-of-the-art AutoML frameworks such as TPOT, AutoWEKA, AutoSklearn, H2O AutoML, GAMA, Asynchronous Successive Halving, and random search.