TSMixer: An all-MLP Architecture for Time Series Forecasting. (arXiv:2303.06053v3 [cs.LG] UPDATED)


TSMixer: An all-MLP Architecture for Time Series Forecasting. (arXiv:2303.06053v3 [cs.LG] UPDATED)
By: <a href="http://arxiv.org/find/cs/1/au:+Chen_S/0/1/0/all/0/1">Si-An Chen</a>, <a href="http://arxiv.org/find/cs/1/au:+Li_C/0/1/0/all/0/1">Chun-Liang Li</a>, <a href="http://arxiv.org/find/cs/1/au:+Yoder_N/0/1/0/all/0/1">Nate Yoder</a>, <a href="http://arxiv.org/find/cs/1/au:+Arik_S/0/1/0/all/0/1">Sercan O. Arik</a>, <a href="http://arxiv.org/find/cs/1/au:+Pfister_T/0/1/0/all/0/1">Tomas Pfister</a> Posted: June 23, 2023

Real-world time-series datasets are often multivariate with complex dynamics.
To capture this complexity, high capacity architectures like recurrent- or
attention-based sequential deep learning models have become popular. However,
recent work demonstrates that simple univariate linear models can outperform
such deep learning models on several commonly used academic benchmarks.
Extending them, in this paper, we investigate the capabilities of linear models
for time-series forecasting and present Time-Series Mixer (TSMixer), a novel
architecture designed by stacking multi-layer perceptrons (MLPs). TSMixer is
based on mixing operations along both the time and feature dimensions to
extract information efficiently. On popular academic benchmarks, the
simple-to-implement TSMixer is comparable to specialized state-of-the-art
models that leverage the inductive biases of specific benchmarks. On the
challenging and large scale M5 benchmark, a real-world retail dataset, TSMixer
demonstrates superior performance compared to the state-of-the-art
alternatives. Our results underline the importance of efficiently utilizing
cross-variate and auxiliary information for improving the performance of time
series forecasting. We present various analyses to shed light into the
capabilities of TSMixer. The design paradigms utilized in TSMixer are expected
to open new horizons for deep learning-based time series forecasting. The
implementation is available at
https://github.com/google-research/google-research/tree/master/tsmixer

Provided by:
http://arxiv.org/icons/sfx.gif

DoctorMorDi

DoctorMorDi

Moderator and Editor