DistDF replaces biased MSE training in time-series forecasting with a tractable joint Wasserstein discrepancy that upper-bounds the desired conditional distributional alignment.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment
DistDF replaces biased MSE training in time-series forecasting with a tractable joint Wasserstein discrepancy that upper-bounds the desired conditional distributional alignment.