HyperJump: Accelerating HyperBand via Risk Modelling

In the literature on hyper-parameter tuning, a number of recent solutions rely on low-fidelity observations (e.g., training with sub-sampled datasets) to identify promising configurations to be tested via high-fidelity observations (e.g., using the full dataset). Among these, HyperBand is arguably one of the most popular solutions, due to its efficiency and theoretically provable robustness. In this work, we introduce HyperJump, a new approach that builds on HyperBand’s robust search strategy and complements it with novel model-based risk analysis techniques that accelerate the search by skipping the evaluation of low risk configurations, i.e., configurations that are likely to be eventually discarded by HyperBand. We evaluate HyperJump on a suite of hyper-parameter optimization problems and show that it provides over one-order of magnitude speed-ups, both in sequential and parallel deployments, on a variety of deep-learning, kernel-based learning and neural architectural search problems when compared to HyperBand and to several state-of-the-art optimizers.

Authors

• Pedro Mendes INESC-ID and Instituto Superior Técnico, Universidade de Lisboa Software and Societal Systems Department, Carnegie Mellon University
• Maria Casimiro INESC-ID and Instituto Superior Técnico, Universidade de Lisboa Software and Societal Systems Department, Carnegie Mellon University
• Paolo Romano INESC-ID and Instituto Superior Técnico, Universidade de Lisboa
• David Garlan Software and Societal Systems Department, Carnegie Mellon University

Keywords

• ML: Auto ML and Hyperparameter Tuning