[3D5-GS-2] Machine learning: Time series

[3D5-GS-2-01] Leveraging Latent Space Symmetry for Time Series Prediction

〇Seong Cheol Jeong¹, Yuki Goto^2,4, Kei Tsukamoto¹, Makoto Kawano¹, Akiyoshi Sannai³, Yutaka Matsuo¹, Wataru Kumagai^1,4 (1. The University of Tokyo, 2. Keio University, 3. Kyoto University, 4. RIKEN AIP)

Keywords:Symmetory, Time Series Prediction, Machine Learning, Latent Space

In machine learning, exploiting symmetry in data is crucial to improving both learning efficiency and accuracy.
Symmetry detection algorithms in time series data have received much attention in unsupervised learning to uncover
the core physical principles of the data. Most existing work focuses on basic two-dimensional symmetry and is
inadequate to handle more complex forms, such as the three-dimensional rotations that are common in real-world
scenarios. To overcome this limitation, we introduce a new model that can learn such complex symmetries in
uniformly varying time series data. Unlike conventional approaches that exploit symmetries in data space, our
model adopts a latent variable framework and assumes existing symmetries in this latent space. By applying the
identifiability theory of nonlinear ICA, we theoretically and experimentally prove that the symmetries detected by
our method are consistent with the true symmetries from time series data whose symmetries are broken in data
space.