HyperJump: Accelerating HyperBand via Risk Modelling. (arXiv:2108.02479v3 [cs.LG] UPDATED)

In the literature on hyper-parameter tuning, a number of recent solutions
rely on low-fidelity observations (e.g., training with sub-sampled datasets or
for short periods of time) to extrapolate good configurations to use when
performing full training. 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 …

arxiv modelling risk