On Hyper-parameter Tuning for Stochastic Optimization Algorithms
arXiv:2003.02038
Abstract
This paper proposes the first-ever algorithmic framework for tuning hyper-parameters of stochastic optimization algorithm based on reinforcement learning. Hyper-parameters impose significant influences on the performance of stochastic optimization algorithms, such as evolutionary algorithms (EAs) and meta-heuristics. Yet, it is very time-consuming to determine optimal hyper-parameters due to the stochastic nature of these algorithms. We propose to model the tuning procedure as a Markov decision process, and resort the policy gradient algorithm to tune the hyper-parameters. Experiments on tuning stochastic algorithms with different kinds of hyper-parameters (continuous and discrete) for different optimization problems (continuous and discrete) show that the proposed hyper-parameter tuning algorithms do not require much less running times of the stochastic algorithms than bayesian optimization method. The proposed framework can be used as a standard tool for hyper-parameter tuning in stochastic algorithms.
arXiv commentOur explanation of reinforcement learning for adjustment algorithm is far fetched in Section ?B
References in corpus (13)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Practical Bayesian Optimization of Machine Learning Algorithms
- ADADELTA: An Adaptive Learning Rate Method
- Playing Atari with Deep Reinforcement Learning
- A Brief Survey of Deep Reinforcement Learning
- Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design
- On First-Order Meta-Learning Algorithms
- Scalable Bayesian Optimization Using Deep Neural Networks
- Learning to Learn without Gradient Descent by Gradient Descent
- A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
- Bayesian Optimization with Exponential Convergence
- Exponential Regret Bounds for Gaussian Process Bandits with Deterministic Observations
- Learning to Warm-Start Bayesian Hyperparameter Optimization