Hyper-parameter Tuning under a Budget Constraint
This addresses a practical problem for machine learning practitioners who need efficient hyper-parameter tuning under limited computational resources, representing an incremental improvement over prior methods.
The paper tackles the problem of hyper-parameter tuning under a hard resource constraint by proposing a sequential decision-making algorithm that dynamically allocates budget based on partial training progress, achieving superior performance over existing state-of-the-art methods on real-world tasks across various budgets.
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.