Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
STEB: In Search of the Best Evaluation Approach for Synthetic Time Series
Michael Stenger, Robert Leppich, André Bauer +1
The growing need for synthetic time series, due to data augmentation or privacy regulations, has led to numerous generative models, frameworks, and evaluation measures alike. Objec…
cs.LG2025
TSRM: A Lightweight Temporal Feature Encoding Architecture for Time Series Forecasting and Imputation
Robert Leppich, Michael Stenger, Daniel Grillmeyer +2
We introduce a temporal feature encoding architecture called Time Series Representation Model (TSRM) for multivariate time series forecasting and imputation. The architecture is st…
cs.LG2024
Time Series Representation Models
Robert Leppich, Vanessa Borst, Veronika Lesch +1
Time series analysis remains a major challenge due to its sparse characteristics, high dimensionality, and inconsistent data quality. Recent advancements in transformer-based techn…