Research map / Probabilistic and scientific modeling / Variational and generative sampling
Latent Process Models for Functional Network Data
Peter W. MacDonald, Elizaveta Levina, Ji Zhu
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 |
|---|---|---|---|
| increase the number of snapshots m | FASE · scenario (i) Gaussian B-spline | Err_Z | Improved |
| increase the number of snapshots m | ASE, OMNI, COSIE · scenario (i) Gaussian B-spline | Err_Z | No clear effect |
| increase the number of nodes n | ASE and FASE · scenario (i) Gaussian B-spline | Err_Z | Improved |
| share information globally across snapshots (OMNI, COSIE) instead of local smoothing | OMNI, COSIE · scenario (i) Gaussian B-spline | Err_Z | Hurt |
| select d and q adaptively with NGCV instead of oracle | FASE · scenario (i) Gaussian B-spline | Err_Z | No clear effect |
| use coordinate descent instead of full grid search for NGCV tuning (ablation) | FASE tuning · scenarios (i)-(iii) | number of models fit: fits around 1/2 to 2/3 as many models | Improved |
| use coordinate descent instead of full grid search for NGCV tuning (ablation) | FASE tuning · scenario (i) | Ratio: 1.016 -> 1.039 at d=2, sigma=8 | No clear effect |
| increase noise sigma from 6 to 8 under NGCV selection | FASE tuning · scenario (i) d=4 | d-Prop (grid): 0.96 -> 0.66 | Hurt |
| move from scenario (i) to scenario (ii) for NGCV selection | FASE tuning · scenario (ii) d=4, sigma=6 | Prop (grid): 0.48 -> 0.24 | Hurt |
| lower RDPG edge density from 1/4 to 1/10 | FASE tuning · scenario (iii) d=2 | Prop (grid): 1.00 -> 0.74 | Hurt |
| lower RDPG edge density | ASE · scenario (iii) RDPG | Err_Z | Hurt |
| lower RDPG edge density | COSIE, OMNI · scenario (iii) RDPG | Err_Z | Improved |
Closest papers by meaning
- Context-dependent Networks in Multivariate Time Series: Models, Methods, and Risk Bounds in High Dimensions (JMLR 2021 · similarity 0.87)
- Learning Vector Autoregressive Models With Latent Processes (AAAI 2018 · similarity 0.86)
- Sparse and low-rank multivariate Hawkes processes (JMLR 2020 · similarity 0.86)
- Neural Latent Space Model for Dynamic Networks and Temporal Knowledge Graphs (AAAI 2021 · similarity 0.86)
- Estimating Diffusion Networks: Recovery Conditions, Sample Complexity and Soft-thresholding Algorithm (JMLR 2016 · similarity 0.86)
- On the Effect of Misspecifying the Embedding Dimension in Low-rank Network Models (ICML 2026 · 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.
