Meta learning for hyperparameter optimization in dialogue system

Jen Tzung Chien, Wei Xiang Lieow

Research output: Contribution to journalConference articlepeer-review

12 Scopus citations

Abstract

The performance of dialogue system based on deep reinforcement learning (DRL) highly depends on the selected hyperparameters in DRL algorithms. Traditionally, Gaussian process (GP) provides a probabilistic approach to Bayesian optimization for sequential search which is beneficial to select optimal hyperparameter. However, GP suffers from the expanding computation when the dimension of hyperparameters and the number of search points are increased. This paper presents a meta learning approach to carry out multifidelity Bayesian optimization where a two-level recurrent neural network (RNN) is developed for sequential learning and optimization. The search space is explored via the first-level RNN with cheap and low fidelity over a global region of hyperparameters. The optimization is then exploited and leveraged by the second-level RNN with a high fidelity on the successively small regions. The experiments on the hyperparameter optimization for dialogue system based on the deep Q network show the effectiveness and efficiency by using the proposed multifidelity Bayesian optimization.

Keywords

  • Bayesian optimization
  • Dialogue system
  • Meta learning
  • Recurrent neural network

Fingerprint

Dive into the research topics of 'Meta learning for hyperparameter optimization in dialogue system'. Together they form a unique fingerprint.

Cite this