Fast and Slow Streams for Online Time Series Forecasting Without Information Leakage

Ying Yee Ava Lau, Zhiwen Shao, D. Yeung
2/12/2026

No official code found. Best implementation: yyalau/iclr2025_dsof (18 stars, PyTorch, last commit 2025-04-30).

Semantic Scholar

Code Implementations(1)

yyalau/iclr2025_dsofCommunity57%
PyTorch

This is the official repository for the ICLR 2025 Conference Paper - Fast and Slow Streams for Online Time Series Forecasting without Information Leakage.

182PythonFeb 22, 20251 years ago
deep-learningpytorchtime-series-forecasting

Similar Papers

Streaming Algorithms and Lower Bounds for Estimating Correlation Clustering Cost

99% match2026

Phase Concentration and Shortcut Suppression for Weakly Supervised Semantic Segmentation

99% match1 repo22026

Batch Singular Value Polarization and Weighted Semantic Augmentation for Universal Domain Adaptation

99% match2026

Slimmed Asymmetrical Contrastive Learning and Cross Distillation for Lightweight Model Training

99% match2026

Towards Optimal Caching and Model Selection for Large Model Inference

99% match2026

Vision and Language Synergy for Rehearsal Free Continual Learning

99% match2026

Cite this paper

@article{lau2026fast,
  title  = {Fast and Slow Streams for Online Time Series Forecasting Without Information Leakage},
  author = {Ying Yee Ava Lau and Zhiwen Shao and D. Yeung},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:08d68bf827f5b45fae571fdacb9346faab95ff8c},
  journal = {ICLR 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/08d68bf827f5b45fae571fdacb9346faab95ff8c.svg)](https://codeofpaper.com/paper/08d68bf827f5b45fae571fdacb9346faab95ff8c)

Discussion