Research map / Time series / Causal and generative time series
On the Constrained Time-Series Generation Problem
Andrea Coletta, Sriram Gopalakrishnan, Daniel Borrajo, Svitlana Vyetrenko
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use DiffTime instead of TimeGAN for unconstrained generation | time-series generation · Sines | Predictive Score: .093 $\pm$ .019 -> .093 $\pm$ .000 | Improved |
| Use DiffTime instead of GT-GAN for unconstrained generation | time-series generation · Stocks | Predictive Score: .040 $\pm$ .000 -> .038 $\pm$ .001 | Improved |
| Use COP instead of GT-GAN for unconstrained generation | time-series generation · Energy | Discriminative Score: .221 $\pm$ .068 -> \textbf{.101 $\pm$ .019} | Improved |
| Condition generation on a trend | DiffTime · Stocks Open trend | Perc. Error Distance: 0.071±0 -> 0.018±0 | Improved |
| Guide sampling with the global-minimum constraint | GuidedDiffTime · Stocks Open global minimum | Satisfaction Rate: 0.87±0.02 -> 0.90±0.01 | Improved |
| Guide sampling with the multivariate OHLC constraint | GuidedDiffTime · Stocks OHLC multivariate | Satisfaction Rate: 0.51±0.02 -> 0.72±0.02 | Improved |
| Enforce fixed-point values during diffusion steps | DiffTime · Stocks two fixed points | Satisfaction Rate: 0.00±0.00 -> \B 1.00±0.00 | Improved |
| Use inference-time constraint guidance rather than constraint-specific retraining | GuidedDiffTime · new constraints | carbon footprint reduction: up to $92\% | Improved |
Closest papers by meaning
- Generating Financial Time Series by Matching Random Convolutional Features (NeurIPS 2026 · similarity 0.86)
- FIDE: Frequency-Inflated Conditional Diffusion Model for Extreme-Aware Time Series Generation (NeurIPS 2024 · similarity 0.86)
- TSGM: A Flexible Framework for Generative Modeling of Synthetic Time Series (NeurIPS 2024 · similarity 0.85)
- Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approach (NeurIPS 2025 · similarity 0.85)
- Conditional Diffusion Model with Nonlinear Data Transformation for Time Series Forecasting (ICML 2025 · similarity 0.85)
- TimeES: Probabilistic and Deterministic Time Series Forecasting via Evolutionary Spectra (NeurIPS 2026 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
