mlsanityData to 7 Oct 2026

TimeBridge: Better Diffusion Prior Design with Bridge Models for Time Series Generation

arXiv 2408.06672 ↗First posted 13 Aug 2024cs.LG cs.AIcited by 5

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Time series generation is widely used in real-world applications such as simulation, data augmentation, and hypothesis testing. Recently, diffusion models have emerged as the de facto approach to time series generation, enabling diverse synthesis scenarios. However, the fixed standard-Gaussian diffusion prior may be ill-suited for time series data, which exhibit properties such as temporal order and fixed time points. In this paper, we propose TimeBridge, a framework that flexibly synthesizes time series data by using diffusion bridges to learn paths between a chosen prior and the data distribution. We then explore several prior designs tailored to time series synthesis. Our framework covers (i) data- and time-dependent priors for unconditional generation and (ii) scale-preserving priors for conditional generation. Experiments show that our framework with data-driven priors outperforms standard diffusion models on time series generation.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 30 of its 56 references that are in the map. First posted on arXiv 13 Aug 2024.

Builds on

30 of 56 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Diffusion-TS: Interpretable Diffusion for General Time Series Generation4 Mar
  2. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation7 Jul

Other references · 28

  1. 2020Denoising Diffusion Implicit Modelscited by 9,655
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  3. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  4. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  5. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  6. 2021Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modelingcited by 594
  7. 2021TS2Vec: Towards Universal Representation of Time Seriescited by 463
  8. 2020A Transformer-based Framework for Multivariate Time Series Representation Learningcited by 449
  9. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 445
  10. 2022Flexible Diffusion Modeling of Long Videoscited by 294
  11. 2020Time Series Data Augmentation for Deep Learning: A Surveycited by 225
  12. 2022BBDM: Image-to-image Translation with Brownian Bridge Diffusion Modelscited by 222
16 more
  1. 2021Likelihood Training of Schr"odinger Bridge using Forward-Backward SDEs Theorycited by 216
  2. 2023I2SB: Image-to-Image Schr"odinger Bridgecited by 214
  3. 2021Solving Schr"odinger Bridges via Maximum Likelihoodcited by 140
  4. 2021TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generationcited by 139
  5. 2022CARD: Classification and Regression Diffusion Modelscited by 102
  6. 2021PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Priorcited by 78
  7. 2020COT-GAN: Generating Sequential Data via Causal Optimal Transportcited by 70
  8. 2021PSA-GAN: Progressive Self Attention GANs for Synthetic Time Seriescited by 58
  9. 2023On the Constrained Time-Series Generation Problemcited by 52
  10. 2023Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEscited by 48
  11. 2022Modeling Temporal Data as Continuous Functions with Stochastic Process Diffusioncited by 39
  12. 2022Deep Latent State Space Models for Time-Series Generationcited by 37
  13. 2024Time Series Diffusion in the Frequency Domaincited by 35
  14. 2023Generative modeling for time series via Schr"odinger bridgecited by 18
  15. 2023Market-GAN: Adding Control to Financial Market Data Generation with Semantic Contextcited by 13
  16. 2024Soft-constrained Schrodinger Bridge: a Stochastic Control Approachcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 3.

5 papers.

  1. 2024Series-to-Series Diffusion Bridge Modelcited by 3
  2. 2025How to Unlock Time Series Editing? Diffusion-Driven Approach with Multi-Grained Controlcited by 1
  3. 2026Rectified Schr"odinger Bridge Matching for Few-Step Visual Navigationcited by 1
  4. 2026E4GEN: Event-level Explainable Extreme-Enhanced Time-series Generationcited by 1
  5. 2026Seq-Flow: Efficient Probabilistic Forecasting with Self-Rollout Error Controlcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Exploiting the Prior of Generative Time Series Imputation
  2. 2025WaveStitch: Flexible and Fast Conditional Time Series Generation with Diffusion Models
  3. 2023Diffusion Models for Time Series Applications: A Survey
  4. 2025DS-Diffusion: Data Style-Guided Diffusion Model for Time-Series Generation
  5. 2026ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space
  6. 2025TIMED: Adversarial and Autoregressive Refinement of Diffusion-Based Time Series Generation
  7. 2025Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approach
  8. 2025Population Aware Diffusion for Time Series Generation