Designing Time-Series Models With Hypernetworks & Adversarial Portfolios
This work addresses time-series forecasting and portfolio optimization for competitions, offering incremental improvements in meta-learning techniques.
The authors tackled forecasting and investment challenges in the M6 competition by developing a meta-learning model using hypernetworks to design parametric models for time-series forecasting, achieving 4th and 6th place in the challenges and 1st overall, and demonstrated superiority over state-of-the-art methods in tasks like sinusoidal regression and M4 competition data.
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.