mlsanityData to 14 Oct 2026

ANT: Adaptive Noise Schedule for Time Series Diffusion Models

arXiv 2410.14488 ↗First posted 18 Oct 2024cs.LG cs.AI stat.MLcited by 11

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

Abstract (arXiv)

Advances in diffusion models for generative artificial intelligence have recently propagated to the time series (TS) domain, demonstrating state-of-the-art performance on various tasks. However, prior works on TS diffusion models often borrow the framework of existing works proposed in other domains without considering the characteristics of TS data, leading to suboptimal performance. In this work, we propose Adaptive Noise schedule for Time series diffusion models (ANT), which automatically predetermines proper noise schedules for given TS datasets based on their statistics representing non-stationarity. Our intuition is that an optimal noise schedule should satisfy the following desiderata: 1) It linearly reduces the non-stationarity of TS data so that all diffusion steps are equally meaningful, 2) the data is corrupted to the random noise at the final step, and 3) the number of steps is sufficiently large. The proposed method is practical for use in that it eliminates the necessity of finding the optimal noise schedule with a small additional cost to compute the statistics for given datasets, which can be done offline before training. We validate the effectiveness of our method across various tasks, including TS forecasting, refinement, and generation, on datasets from diverse domains. Code is available at this repository: https://github.com/seunghan96/ANT.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 24 of its 40 references that are in the map. First posted on arXiv 18 Oct 2024.

Builds on

24 of 40 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Process9 Mar
  2. 2024Diffusion-TS: Interpretable Diffusion for General Time Series Generation4 Mar
  3. 2023Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting21 Jul
  4. 2023Non-autoregressive Conditional Diffusion Models for Time Series Prediction8 Jun
  5. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation7 Jul
  6. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting28 Jan

Other references · 18

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2022Generative Adversarial Networkscited by 5,627
  5. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  6. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  7. 2023Consistency Modelscited by 1,822
  8. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  9. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
  10. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  11. 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 761
  12. 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 310
6 more
  1. 2017A Multi-Horizon Quantile Recurrent Forecastercited by 211
  2. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 198
  3. 2023On the Importance of Noise Scheduling for Diffusion Modelscited by 194
  4. 2021TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generationcited by 142
  5. 2023Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglementcited by 90
  6. 2021ScoreGrad: Multivariate Probabilistic Time Series Forecasting with Continuous Energy-based Generative Modelscited by 43

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 5.

11 papers.

  1. 2025Non-stationary Diffusion For Probabilistic Time Series Forecastingcited by 27
  2. 2025MRI super-resolution reconstruction using efficient diffusion probabilistic model with residual shiftingcited by 10
  3. 2024Exploring Diffusion and Flow Matching Under Generator Matchingcited by 9
  4. 2025Theoretical Foundation of Flow-Based Time Series Generation: Provable Approximation, Generalization, and Efficiencycited by 2
  5. 2025DS-Diffusion: Data Style-Guided Diffusion Model for Time-Series Generationcited by 2
  6. 2026StaTS: Spectral Trajectory Schedule Learning for Adaptive Time Series Forecasting with Frequency Guided Denoisercited by 1
  7. 2025Alternators With Noise Modelscited by 0
  8. 2026Parametric Prior Mapping Framework for Non-stationary Probabilistic Time Series Forecastingcited by 0
  9. 2026Towards a Unified Generative Model for Scarce Time Series with Domain Expertscited by 0
  10. 2026When Denoising Hurts: Rethinking the Terminal Step of Diffusion Time Series Forecasters -- Extended Versioncited by 0
  11. 2026EXAONE Demand 1.0: A Time Series Foundation Model for Demand Forecastingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024The Rise of Diffusion Models in Time-Series Forecasting
  2. 2025Diffusion Models for Time Series Forecasting: A Survey
  3. 2023Diffusion Models for Time Series Applications: A Survey
  4. 2026DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting
  5. 2025ADiff4TPP: Asynchronous Diffusion Models for Temporal Point Processes
  6. 2026A Decomposable Forward Process in Diffusion Models for Time-Series Forecasting
  7. 2024Constant Rate Scheduling: A General Framework for Optimizing Diffusion Noise Schedule via Distributional Change
  8. 2024Series-to-Series Diffusion Bridge Model