Sign in

SutraNets: Sub-series Autoregressive Networks for Long-Sequence, Probabilistic Forecasting

By Shane Bergsma and others
We propose SutraNets, a novel method for neural probabilistic forecasting of long-sequence time series. SutraNets use an autoregressive generative model to factorize the likelihood of long sequences into products of conditional probabilities. When generating long sequences, most autoregressive approaches suffer from harmful error accumulation, as well as challenges in modeling... Show more
December 22, 2023
=
0
Loading PDF…
Loading full text...
Similar articles
Loading recommendations...
=
0
x1
SutraNets: Sub-series Autoregressive Networks for Long-Sequence, Probabilistic Forecasting
Click on play to start listening