Population-based Global Optimisation Methods for Learning Long-term Dependencies with RNNs

Abstract

Despite recent innovations in network architectures and loss functions, training RNNs to learn long-term dependencies remains difficult due to challenges with gradient-based optimisation methods. Inspired by the success of Deep Neuroevolution in reinforcement learning (Such et al. 2017), we explore the use of gradient-free population-based global optimisation (PBO) techniques -- training RNNs to capture long-term dependencies in time-series data. Testing evolution strategies (ES) and particle swarm optimisation (PSO) on an application in volatility forecasting, we demonstrate that PBO methods lead to performance improvements in general, with ES exhibiting the most consistent results across a variety of architectures.

To appear at ICML 2019 Time Series Workshop

References in corpus (4)

• Evolution Strategies as a Scalable Alternative to Reinforcement Learning
• Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
• DeepLOB: Deep Convolutional Neural Networks for Limit Order Books
• h-detach: Modifying the LSTM Gradient Towards Better Optimization