3 papers
cs.LG2025
PRISM: A hierarchical multiscale approach for time series forecasting
Zihao Chen, Alexandre Andre, Wenrui Ma +3
Forecasting is critical in areas such as finance, biology, and healthcare. Despite the progress in the field, making accurate forecasts remains challenging because real-world time…
cs.LG2024
Generalizable autoregressive modeling of time series through functional narratives
Ran Liu, Wenrui Ma, Ellen Zippi +8
Time series data are inherently functions of time, yet current transformers often learn time series by modeling them as mere concatenations of time periods, overlooking their funct…
cs.LG2024
Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance
Chiraag Kaushik, Ran Liu, Chi-Heng Lin +5
Classification models are expected to perform equally well for different classes, yet in practice, there are often large gaps in their performance. This issue of class bias is wide…