Designing Time-Series Models With Hypernetworks & Adversarial Portfolios

TL;DR

This paper introduces a novel meta-learning approach using hypernetworks for time-series forecasting, achieving top rankings in a major competition and outperforming existing models in various tasks.

Contribution

It presents a new hypernetwork-based meta-learning model for time-series forecasting that is trainable via backpropagation and adaptable to different tasks, outperforming state-of-the-art methods.

Findings

Achieved 4th and 6th place in forecasting and investment challenges of M6 competition.

Outperformed state-of-the-art meta-learning methods in sinusoidal regression.

Surpassed conventional parametric models on M4 time-series data.

Abstract

This article describes the methods that achieved 4th and 6th place in the forecasting and investment challenges, respectively, of the M6 competition, ultimately securing the 1st place in the overall duathlon ranking. In the forecasting challenge, we tested a novel meta-learning model that utilizes hypernetworks to design a parametric model tailored to a specific family of forecasting tasks. This approach allowed us to leverage similarities observed across individual forecasting tasks while also acknowledging potential heterogeneity in their data generating processes. The model's training can be directly performed with backpropagation, eliminating the need for reliance on higher-order derivatives and is equivalent to a simultaneous search over the space of parametric functions and their optimal parameter values. The proposed model's capabilities extend beyond M6, demonstrating superiority over state-of-the-art meta-learning methods in the sinusoidal regression task and outperforming conventional parametric models on time-series from the M4 competition. In the investment challenge, we adjusted portfolio weights to induce greater or smaller correlation between our submission and that of other participants, depending on the current ranking, aiming to maximize the probability of achieving a good rank.