ES-ENAS: Efficient Evolutionary Optimization for Large Hybrid Search Spaces
This addresses the curse of dimensionality in evolutionary algorithms for hybrid search spaces, offering a more efficient method for tasks like neural architecture search, though it appears incremental as it combines existing techniques.
The paper tackles the problem of optimizing blackbox functions over large hybrid search spaces with both combinatorial and continuous parameters, proposing ES-ENAS to improve sample efficiency, which is demonstrated empirically over synthetic benchmarks and applied to architecture search in RL benchmarks.
In this paper, we approach the problem of optimizing blackbox functions over large hybrid search spaces consisting of both combinatorial and continuous parameters. We demonstrate that previous evolutionary algorithms which rely on mutation-based approaches, while flexible over combinatorial spaces, suffer from a curse of dimensionality in high dimensional continuous spaces both theoretically and empirically, which thus limits their scope over hybrid search spaces as well. In order to combat this curse, we propose ES-ENAS, a simple and modular joint optimization procedure combining the class of sample-efficient smoothed gradient techniques, commonly known as Evolutionary Strategies (ES), with combinatorial optimizers in a highly scalable and intuitive way, inspired by the one-shot or supernet paradigm introduced in Efficient Neural Architecture Search (ENAS). By doing so, we achieve significantly more sample efficiency, which we empirically demonstrate over synthetic benchmarks, and are further able to apply ES-ENAS for architecture search over popular RL benchmarks.