Zi Ciu Chan — accepted AI-conference papers

2026

DistDF: Time-series Forecasting Needs Joint-distribution Wasserstein Alignment

Eric Wang, Licheng Pan, Yuan Lu, Zhixuan Chu, Xiaoxi Li, Shuting He +4

ICLR 2026poster

Training time-series forecast models requires aligning the conditional distribution of model forecasts with that of the label sequence. The standard direct forecast (DF) approach seeks to minimize the conditional negative log-likelihood of the label sequence, typically estimated using the mean squa…

Cited by 0 Source ↗code ↗Scholar ↗

2026

Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models

Eric Wang, Licheng Pan, Yuan Lu, Zi Ciu Chan, Tianqiao Liu, Shuting He +4

ICLR 2026poster

The design of training objective is central to training time-series forecasting models. Existing training objectives such as mean squared error mostly treat each future step as an independent, equally weighted task, which we found leading to the following two issues: (1) overlook the *label autocorr…

Cited by 0 Source ↗Scholar ↗