Optimizing Hyperparameters in CNNs using Bilevel Programming in Time Series Data

TL;DR

This paper introduces a bilevel programming approach to optimize hyperparameters in CNNs specifically for time series prediction, aiming to improve model performance.

Contribution

It proposes a novel bilevel programming framework tailored for hyperparameter tuning in CNNs applied to time series data.

Findings

Bilevel programming effectively models hyperparameter optimization.

Framework shows potential for improved CNN performance on time series.

Lays groundwork for future empirical validation.

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.