mlsanityData to 14 Oct 2026

Diffusion-Based Scenario Tree Generation for Multivariate Time Series Prediction and Multistage Stochastic Optimization

arXiv 2509.14832 ↗First posted 18 Sep 2025cs.LG cs.AI cs.SYcited by 0

Not on the map. Why?

Abstract (arXiv)

Stochastic forecasting is critical for efficient decision-making in uncertain systems, such as energy markets and finance, where estimating the full distribution of future scenarios is essential. We propose Diffusion Scenario Tree (DST), a general framework for constructing scenario trees using diffusion-based probabilistic forecasting models to provide a structured model of system evolution for control tasks. DST recursively samples future trajectories and organizes them into a tree via clustering, ensuring non-anticipativity (decisions depending only on observed history) at each stage, offering a superior representation of uncertainty compared to using predictive models solely for forecasting system evolution. We integrate DST into Model Predictive Control (MPC) and evaluate it on energy arbitrage in New York State's day-ahead electricity market. Experimental results show that our approach significantly outperforms the same optimization algorithms that use scenario trees generated by more conventional models. Furthermore, using DST for stochastic optimization yields more efficient decision policies by better handling uncertainty than deterministic and stochastic MPC variants using the same diffusion-based forecaster, and simple Model-Free Reinforcement Learning (RL) baselines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 29 references that are in the map. First posted on arXiv 18 Sep 2025.

Builds on

14 of 29 references.

References · 14

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
  4. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 938
  5. 2022Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learningcited by 562
  6. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecastingcited by 337
  7. 2014From Predictive to Prescriptive Analyticscited by 143
  8. 2023Synthetic Experience Replaycited by 101
  9. 2024TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Modelcited by 33
  10. 2021Reinforcement Learning based on Scenario-tree MPC for ASVscited by 8
  11. 2021Problem-Driven Scenario Clustering in Stochastic Optimizationcited by 6
  12. 2024A Financial Time Series Denoiser Based on Diffusion Modelcited by 6
2 more
  1. 2015Problem-driven scenario generation: an analytical approach for stochastic programs with tail risk measurecited by 5
  2. 2025Diffusion-Based Forecasting for Uncertainty-Aware Model Predictive Controlcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Control-Oriented Scenario Tree Construction through Reinforcement Learning
  2. 2026Diff2SP: Diffusion Models for Correlated Scenario Generation in Stochastic Programming
  3. 2025The day-ahead scenario generation method for new energy based on an improved conditional generative diffusion model
  4. 2026DynG-Diff: A State-Aware Dynamic Guidance Diffusion Framework for Probabilistic Time Series Forecasting
  5. 2022Denoising diffusion probabilistic models for probabilistic energy forecasting
  6. 2023The Bayesian Context Trees State Space Model for time series modelling and forecasting
  7. 2025Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamics
  8. 2026Quantile-Guided Diffusion for Probabilistic Time-Series Forecasting