Research map / Time series / Causal and generative time series
Deep Poisson gamma dynamical systems
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 three hidden layers instead of two (ablation) | DPGDS · GDELT | MP: 0.688 -> 0.689 | No clear effect |
| Use three hidden layers instead of two (ablation) | DPGDS · ICEWS | PP: 0.473 -> 0.478 | Helped |
| Use three hidden layers instead of two (ablation) | DPGDS · SOTU | PP: 0.622 -> 0.628 | Helped |
| Use three hidden layers instead of two (ablation) | DPGDS · DBLP | PP: 0.582 -> 0.600 | Helped |
| Use three hidden layers instead of two (ablation) | DPGDS · NIPS | PP: 0.814 -> 0.839 | Helped |
| Use three hidden layers rather than a shallow dynamic model | DPGDS · GDELT | PP: 0.447 -> 0.456 | Helped |
| Use three hidden layers rather than a shallow dynamic model | DPGDS · ICEWS | PP: 0.465 -> 0.478 | Helped |
| Use three hidden layers rather than a shallow dynamic model | DPGDS · SOTU | PP: 0.617 -> 0.628 | Helped |
| Use three hidden layers rather than a shallow dynamic model | DPGDS · DBLP | PP: 0.581 -> 0.600 | Helped |
| Use three hidden layers rather than a shallow dynamic model | DPGDS · NIPS | PP: 0.807 -> 0.839 | Helped |
| Use DPGDS instead of DTSBN | DPGDS · bouncing ball synthetic sequences | prediction error | Helped |
| Use mini-batch SGMCMC inference | DPGDS · GDELT 2001–2005 | MP | Helped |
Closest papers by meaning
- Poisson-Gamma dynamical systems (NeurIPS 2016 · similarity 0.92)
- Poisson-Randomized Gamma Dynamical Systems (NeurIPS 2019 · similarity 0.91)
- Deep Dynamic Poisson Factorization Model (NeurIPS 2017 · similarity 0.88)
- Fully Heteroscedastic Count Regression with Deep Double Poisson Networks (ICML 2025 · similarity 0.86)
- eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modeling (NeurIPS 2024 · similarity 0.85)
- Out-of-Domain Generalization in Dynamical Systems Reconstruction (ICML 2024 · 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.