Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
WinoTS: Wavelet-based Self-Distillation for Time Series Models
Noam Major, Kathy Razmadze, Yoli Shavit
Self-supervised pre-training of time series models is currently dominated by next-token prediction and reconstruction objectives. In continuous-valued domains, these paradigms ofte…
cs.LG2026
When Does Self-Supervised Learning Transfer to Time-Series Tasks?
Noam Major, Kathy Razmadze, Yoli Shavit
Self-supervised learning (SSL) assumes that solving pretext tasks on unlabeled data yields representations that transfer effectively across downstream applications via linear probi…