Research map / Time series / Causal and generative time series
PCF-GAN: generating sequential data via the characteristic function of measures on the path space
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 PCF-GAN instead of best baseline (RGAN) | time series generation · RV | discriminative score: .0271 -> .0108 | Helped |
| use PCF-GAN instead of best baseline (RGAN) | time series generation · Stock | discriminative score: .1283 -> .0784 | Helped |
| use PCF-GAN instead of TimeGAN | time series generation · Air | discriminative score: .3460 -> .2326 | Helped |
| use PCF-GAN instead of TimeGAN | time series generation · EEG | discriminative score: .4771 -> .3660 | Helped |
| use PCF-GAN instead of best baseline | time series generation · EEG | predictive score: .0304 -> .0246 | Helped |
| use PCF-GAN instead of RGAN | time series generation · RV | predictive score: .0393 -> .0390 | No clear effect |
| use PCF-GAN instead of COT-GAN | time series generation · EEG | Sig-MMD: .0102 -> .0180 | Hurt |
| use PCF-GAN instead of TimeGAN | time series generation · RV | Sig-MMD: .0027 -> .0024 | Helped |
| use PCF-GAN autoencoder instead of TimeGAN for reconstruction | reconstruction · RV | Sig-MMD: 3.308 -> .0960 | Helped |
| use PCF-GAN autoencoder instead of TimeGAN for reconstruction | reconstruction · Stock | Sig-MMD: .7587 -> .0078 | Helped |
| use PCF-GAN autoencoder instead of TimeGAN for reconstruction | reconstruction · Stock | predictive score: .1180 -> .0127 | Helped |
| use PCF-GAN autoencoder instead of TimeGAN for reconstruction | reconstruction · EEG | discriminative score: .5000 -> .4959 | Helped |
Closest papers by meaning
- Time-series Generative Adversarial Networks (NeurIPS 2019 · similarity 0.90)
- GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networks (NeurIPS 2022 · similarity 0.88)
- AEC-GAN: Adversarial Error Correction GANs for Auto-Regressive Long Time-Series Generation (AAAI 2023 · similarity 0.87)
- MCGAN: Enhancing GAN Training with Regression-Based Generator Loss (AAAI 2025 · similarity 0.86)
- Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs (ICLR 2024 · similarity 0.86)
- Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approach (NeurIPS 2025 · similarity 0.85)
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.