Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Does Normalization Choice Matter for Causal Large Time-Series Models?
Samy-Melwan Vilhes, Gilles Gasso, Mokhtar Z Alaya
Large models for time-series forecasting have been emerged as a promising paradigm for training models on heterogeneous collections of signals. These models typically rely on causa…
cs.LG2024
Gaussian-Smoothed Sliced Probability Divergences
Mokhtar Z. Alaya, Alain Rakotomamonjy, Maxime Berar +1
Gaussian smoothed sliced Wasserstein distance has been recently introduced for comparing probability distributions, while preserving privacy on the data. It has been shown that it…
cs.LG2021
Heterogeneous Wasserstein Discrepancy for Incomparable Distributions
Mokhtar Z. Alaya, Gilles Gasso, Maxime Berar +1
Optimal Transport (OT) metrics allow for defining discrepancies between two probability measures. Wasserstein distance is for longer the celebrated OT-distance frequently-used in t…