Adrien Cortes — accepted AI-conference papers

2025

Winner-takes-all for Multivariate Probabilistic Time Series Forecasting

Adrien Cortes, Remi Rehm, Victor Letzelter

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 0 Source ↗PDF ↗Scholar ↗

2024

Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealing

David Perera, Victor Letzelter, Theo Mariotte, Adrien Cortes, Mickael Chen, Slim Essid +1

NeurIPS 2024poster

We introduce Annealed Multiple Choice Learning (aMCL) which combines simulated annealing with MCL. MCL is a learning framework handling ambiguous tasks by predicting a small set of plausible hypotheses. These hypotheses are trained using the Winner-takes-all (WTA) scheme, which promotes the diversit…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗