← Search

Remi Rehm

2 accepted papers

2025

Winner-takes-all for Multivariate Probabilistic Time Series Forecasting

ICML 2025poster

We introduce $\texttt{TimeMCL}$, a method leveraging the Multiple Choice Learning (MCL) paradigm to forecast multiple plausible time series futures. Our approach employs a neural network with multiple heads and utilizes the Winner-Takes-All (WTA) loss to promote diversity among predictions. MCL has…

Cited by 0SourcePDFScholar