Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2602.00297 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914558951555072 |
|---|---|
| author | Yang, Jie Hu, Yifan Li, Yuante Zhang, Kexin Ding, Kaize Yu, Philip S. |
| author_facet | Yang, Jie Hu, Yifan Li, Yuante Zhang, Kexin Ding, Kaize Yu, Philip S. |
| contents | Deep learning has achieved strong performance in Time Series Forecasting (TSF). However, we identify a critical representation paradox, termed Latent Chaos: models with accurate predictions often learn latent representations that are temporally disordered and lack continuity. We attribute this to the dominant observation-space forecasting paradigm, where minimizing point-wise errors on noisy and partially observed data encourages shortcut solutions instead of the recovery of underlying system dynamics. To address this, we propose Latent Time Series Forecasting (LatentTSF), a paradigm that shifts TSF from observation regression to latent state prediction. LatentTSF employs an AutoEncoder to project each observation into a learned latent state space and performs forecasting entirely in this space, allowing the model to focus on learning structured temporal dynamics. We provide an information-theoretic analysis showing that the latent objectives can be motivated as surrogates for maximizing mutual information between predicted and ground-truth latent states and future observations. Extensive experiments on widely-used benchmarks confirm that LatentTSF effectively mitigates latent chaos, yielding consistent improvements in both forecasting accuracy and representation quality. Our code is available at https://github.com/Muyiiiii/LatentTSF. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_00297 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Observations to States: Latent Time Series Forecasting Yang, Jie Hu, Yifan Li, Yuante Zhang, Kexin Ding, Kaize Yu, Philip S. Machine Learning Deep learning has achieved strong performance in Time Series Forecasting (TSF). However, we identify a critical representation paradox, termed Latent Chaos: models with accurate predictions often learn latent representations that are temporally disordered and lack continuity. We attribute this to the dominant observation-space forecasting paradigm, where minimizing point-wise errors on noisy and partially observed data encourages shortcut solutions instead of the recovery of underlying system dynamics. To address this, we propose Latent Time Series Forecasting (LatentTSF), a paradigm that shifts TSF from observation regression to latent state prediction. LatentTSF employs an AutoEncoder to project each observation into a learned latent state space and performs forecasting entirely in this space, allowing the model to focus on learning structured temporal dynamics. We provide an information-theoretic analysis showing that the latent objectives can be motivated as surrogates for maximizing mutual information between predicted and ground-truth latent states and future observations. Extensive experiments on widely-used benchmarks confirm that LatentTSF effectively mitigates latent chaos, yielding consistent improvements in both forecasting accuracy and representation quality. Our code is available at https://github.com/Muyiiiii/LatentTSF. |
| title | From Observations to States: Latent Time Series Forecasting |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.00297 |