Optimizing Hyperparameters in CNNs using Bilevel Programming in Time Series Data

Abstract

Hyperparameter optimization has remained a central topic within the machine learning community due to its ability to produce state-of-the-art results. With the recent interest growing in the usage of CNNs for time series prediction, we propose the notion of optimizing Hyperparameters in CNNs for the purpose of time series prediction. In this position paper, we give away the idea of modeling the concerned hyperparameter optimization problem using bilevel programming.

References in corpus (5)

• Multi-Scale Convolutional Neural Networks for Time Series Classification
• Gradient-based Hyperparameter Optimization through Reversible Learning
• Conditional Time Series Forecasting with Convolutional Neural Networks
• Bilevel Programming for Hyperparameter Optimization and Meta-Learning
• Multivariate Time Series Classification using Dilated Convolutional Neural Network