Research map / Learning theory and algorithms / Kernels and regression theory
Extending the Modelling Capacity of Gaussian Conditional Random Fields while Learning Faster
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 |
|---|---|---|---|
| allow negative link weight beta (extended parameter space) | GCRF · Synthetic, negative link influence | R2: 0.31 -> 0.56 | Helped |
| allow negative predictor weight alpha2 | GCRF · Synthetic, negative predictor influence | R2: 0.051 -> 0.78 | Helped |
| UmGCRF vs GCRF when all links positive | GCRF · Synthetic, positive links | R2: 0.999 -> 0.999 | No clear effect |
| UmGCRF with learned intercept (bias) term vs GCRF | GCRF · HCUP California hospital admissions | test RMSE: 0.1559 -> 0.1558 | No clear effect |
| eigendecomposition-based gradients (single graph) vs standard GCRF | GCRF · Training time, 10,000 targets | time: 1.76 hours -> 3.9 mins | Helped |
| UmGCRF vs SpGCRF network learning | SpGCRF · Training time, 5,000 targets | time: 28.1 hours -> 43 secs | Helped |
| UmGCRF vs FF-GCRF approximation | FF-GCRF · Training time, 10,000 targets | time: 2.9 mins -> 3.9 mins | Hurt |
Closest papers by meaning
- Structured Regression Gradient Boosting (CVPR 2016 · similarity 0.85)
- Convex Two-Layer Modeling with Latent Structure (NeurIPS 2016 · similarity 0.83)
- Scalable Deep Gaussian Markov Random Fields for General Graphs (ICML 2022 · similarity 0.83)
- Learning Gaussian DAG Models without Condition Number Bounds (ICML 2025 · similarity 0.81)
- GlucoFM-Bench: Benchmarking Time-Series Foundation Models for Blood Glucose Forecasting (NeurIPS 2026 · similarity 0.81)
- Learning Local Neighborhoods of Non-Gaussian Graphical Models (AAAI 2025 · similarity 0.81)
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.