← Search

Tim Zeyl

2 accepted papers

2023

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

NeurIPS 2023poster

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 appro…

Cited by 6SourcePDFScholar
2022

C2FAR: Coarse-to-Fine Autoregressive Networks for Precise Probabilistic Forecasting

NeurIPS 2022accept

We present coarse-to-fine autoregressive networks (C2FAR), a method for modeling the probability distribution of univariate, numeric random variables. C2FAR generates a hierarchical, coarse-to-fine discretization of a variable autoregressively; progressively finer intervals of support are generated…