MarkovTS: Pretrained State-Transition Representations for Zero-Shot Time Series Generation
cs.LG, cs.AI
Submitted: 2026-10-31
Updated: 2026-10-31
Code: https://github.com/blisky-li/MarkovTS
Project page: https://decisionintelligence.github.io/OpenTS/leaderboards/9
License: http://creativecommons.org/licenses/by/4.0/
The gist: Across heterogeneous real-world domains, time-series generation supports simulation, model development…
Terminology
Abstract
Across heterogeneous real-world domains, time-series generation supports simulation, model development, and data augmentation by generating sequences that preserve target-domain statistics and temporal dependencies when real observations are scarce or costly. However, existing methods predominantly address in-domain generation, limiting their reuse in unseen domains. We study reference-conditioned zero-shot time series generation: target domains are unseen during pretraining, generation uses a single target-domain reference sequence, and no model parameters are updated. MarkovTS characterizes sequence evolution through local morphologies and their ordered transitions at multiple temporal scales. Its pretrained encoder quantizes normalized time-series patches into multiscale morphological states with a state codebook, while a transition codebook encodes contextual transitions between adjacent intervals. These transferable state-transition representations condition a pretrained flow-matching model. At generation, the frozen model combines a reference-derived condition with independent Gaussian noise to produce stochastic samples that retain the reference's temporal organization. Across 12 unseen target datasets, MarkovTS outperforms strong baselines in most distributional comparisons and generates diverse, reference-consistent sequences. As downstream augmentation, its samples yield overall gains across forecasting, classification, and anomaly detection benchmarks and diverse model families. Our code is available at https://github.com/blisky-li/MarkovTS.
Sources
- GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation
- The UEA multivariate time series classification archive, 2018
- TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model
- TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation
- Variational Recurrent Auto-Encoders
- Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic Forecasting
- QUALS: Corpus Equilibrium for Universal Forecasting via Pattern Quantization and Learnability Synchronization
- The Multiverse of Time Series Machine Learning: an Archive for Multivariate Time Series Classification
- From Values to Tokens: An LLM-Driven Framework for Context-aware Time Series Forecasting via Symbolic Discretization
- ARIES: Relation Assessment and Model Recommendation for Deep Time Series Forecasting
- CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patching
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis