Critical Hyper-Parameters: No Random, No Cry

Abstract

The selection of hyper-parameters is critical in Deep Learning. Because of the long training time of complex models and the availability of compute resources in the cloud, "one-shot" optimization schemes - where the sets of hyper-parameters are selected in advance (e.g. on a grid or in a random manner) and the training is executed in parallel - are commonly used. It is known that grid search is sub-optimal, especially when only a few critical parameters matter, and suggest to use random search instead. Yet, random search can be "unlucky" and produce sets of values that leave some part of the domain unexplored. Quasi-random methods, such as Low Discrepancy Sequences (LDS) avoid these issues. We show that such methods have theoretical properties that make them appealing for performing hyperparameter search, and demonstrate that, when applied to the selection of hyperparameters of complex Deep Learning models (such as state-of-the-art LSTM language models and image classification models), they yield suitable hyperparameters values with much fewer runs than random search. We propose a particularly simple LDS method which can be used as a drop-in replacement for grid or random search in any Deep Learning pipeline, both as a fully one-shot hyperparameter search or as an initializer in iterative batch optimization.

Cited by in corpus (13)

• On Empirical Comparisons of Optimizers for Deep Learning
• Measuring the Effects of Data Parallelism on Neural Network Training
• Benchmarking in Optimization: Best Practice and Open Issues
• Black-Box Optimization Revisited: Improving Algorithm Selection Wizards through Massive Benchmarking
• Faster Neural Network Training with Data Echoing
• Implicit differentiation of Lasso-type models for hyperparameter optimization
• Using a thousand optimization tasks to learn hyperparameter search strategies
• Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model
• Fully Parallel Hyperparameter Search: Reshaped Space-Filling
• Online Hyper-parameter Learning for Auto-Augmentation Strategy
• A Generalized Faulhaber Inequality, Improved Bracketing Covers, and Applications to Discrepancy
• Open Loop Hyperparameter Optimization and Determinantal Point Processes
• One-Shot Decision-Making with and without Surrogates