Uncertainty-Gated Generative Modeling
Not on the map. Why?
Abstract (arXiv)
Financial time-series forecasting is a high-stakes problem where regime shifts and shocks make point-accurate yet overconfident models dangerous. We propose Uncertainty-Gated Generative Modeling (UGGM), which treats uncertainty as an internal control signal that gates (i) representation via gated reparameterization, (ii) propagation via similarity and confidence routing, and (iii) generation via uncertainty-controlled predictive distributions, together with uncertainty-driven regularization and calibration to curb miscalibration. Instantiated on Weak Innovation AutoEncoder (WIAE-GPF), our UG-WIAE-GPF significantly improves risk-sensitive forecasting, delivering a 63.5% MSE reduction on NYISO (0.3508 rightarrow 0.1281), with improved robustness under shock intervals (mSE: 0.2739 rightarrow 0.1748).
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 6 of its 17 references that are in the map. First posted on arXiv 8 Mar 2026.
Builds on
6 of 17 references.
References · 6
- 2017Attention Is All You Needcited by 60,361
- 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
- 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
- 2024Advancing Multimodal Data Fusion in Pain Recognition: A Strategy Leveraging Statistical Correlation and Human-Centered Perspectivescited by 3
- 2024CauSkelNet: Causal Representation Learning for Human Behaviour Analysiscited by 3
- 2024Probabilistic Forecasting of Real-Time Electricity Market Signals via Interpretable Generative AIcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.
- 2026Task-Aware Delegation Cues for LLM Agentscited by 2
- 2026Task-Aware Delegation Cues for LLM Agents11 Mar 2026