AI RESEARCH
The Procrustean Bed of Time Series: The Optimization Bias in Point-wise Loss Functions
arXiv CS.LG
•
ArXi:2512.18610v3 Announce Type: replace Intuitively, a deterministic time series should be easier to forecast. However, point-wise loss functions (e.g., MSE and MAE), serving as differentiable surrogates for the ideal optimization target, score each timestamp independently and. therefore. disregard temporal dependence. This mismatch induces a systematic optimization bias that cannot be eliminated merely by improving model expressiveness or optimizer.