Hyper-parameter Tuning under a Budget Constraint
arXiv:1902.00532
Abstract
We study a budgeted hyper-parameter tuning problem, where we optimize the tuning result under a hard resource constraint. We propose to solve it as a sequential decision making problem, such that we can use the partial training progress of configurations to dynamically allocate the remaining budget. Our algorithm combines a Bayesian belief model which estimates the future performance of configurations, with an action-value function which balances exploration-exploitation tradeoff, to optimize the final output. It automatically adapts the tuning behaviors to different constraints, which is useful in practice. Experiment results demonstrate superior performance over existing algorithms, including the-state-of-the-art one, on real-world tuning tasks across a range of different budgets.
References in corpus (8)
- Practical Bayesian Optimization of Machine Learning Algorithms
- Model-Based Bayesian Exploration
- Neural Optimizer Search with Reinforcement Learning
- Freeze-Thaw Bayesian Optimization
- Bilevel Programming for Hyperparameter Optimization and Meta-Learning
- Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search
- Forward and Reverse Gradient-Based Hyperparameter Optimization
- Hyperparameter Optimization: A Spectral Approach