EvoSTS Forecasting: Evolutionary Sparse Time-Series Forecasting

TL;DR

This paper introduces EvoSTS, a novel evolutionary algorithm that optimizes LSTM weights for time-series forecasting by minimizing reconstruction loss using sparse coding, demonstrating potential improvements over traditional methods.

Contribution

The paper presents the first use of sparse coding combined with evolutionary algorithms to optimize LSTM weights for time-series forecasting.

Findings

Improvements observed between first and last generation weights.

Sparse coding approach offers a new perspective for model weight optimization.

Some weights showed negligible improvements due to hyperparameter limitations.

Abstract

In this work, we highlight our novel evolutionary sparse time-series forecasting algorithm also known as EvoSTS. The algorithm attempts to evolutionary prioritize weights of Long Short-Term Memory (LSTM) Network that best minimize the reconstruction loss of a predicted signal using a learned sparse coded dictionary. In each generation of our evolutionary algorithm, a set number of children with the same initial weights are spawned. Each child undergoes a training step and adjusts their weights on the same data. Due to stochastic back-propagation, the set of children has a variety of weights with different levels of performance. The weights that best minimize the reconstruction loss with a given signal dictionary are passed to the next generation. The predictions from the best-performing weights of the first and last generation are compared. We found improvements while comparing the weights of these two generations. However, due to several confounding parameters and hyperparameter limitations, some of the weights had negligible improvements. To the best of our knowledge, this is the first attempt to use sparse coding in this way to optimize time series forecasting model weights, such as those of an LSTM network.