Research map / Optimization / Optimizers
Gradient Information for Representation and Modeling
Jie Ding, Robert Calderbank, Vahid Tarokh
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 |
|---|---|---|---|
| use gradient information instead of Shannon information to build the Chow-Liu tree | Chow-Liu tree with Shannon information · protein data, p from 2 to 11 | computation time | Improved |
| use Chow-Liu tree classifier instead of random forest | Random forest · synthetic two-class Gaussian, rho=0.3 | classification accuracy: 0.607 -> 0.610 | Improved |
| use Chow-Liu tree classifier instead of random forest | Random forest · synthetic two-class Gaussian, rho=0.5 | classification accuracy: 0.759 -> 0.829 | Improved |
| use Chow-Liu tree classifier instead of random forest | Random forest · synthetic two-class Gaussian, rho=0.7 | classification accuracy: 0.886 -> 0.965 | Improved |
| use Chow-Liu tree classifier instead of random forest | Random forest · synthetic two-class Gaussian, rho=0.9 | classification accuracy: 0.953 -> 0.994 | Improved |
| use Chow-Liu tree classifier instead of elastic net | Elastic net · synthetic two-class Gaussian, rho=0.7 | classification accuracy: 0.541 -> 0.965 | Improved |
| increase correlation rho from 0.3 to 0.9 | Chow-Liu tree classifier · synthetic two-class Gaussian | classification accuracy: 0.610 -> 0.994 | Improved |
| increase correlation rho from 0.3 to 0.9 | Elastic net · synthetic two-class Gaussian | classification accuracy: 0.535 -> 0.526 | No clear effect |
| use gradient mutual information tree for community discovery on US payroll growth | Algorithm 2 · US state employment growth panel | community structure | No clear effect |
| recover tree structure with gradient information on protein data | Algorithm 1 · protein data | graph structure | No clear effect |
Closest papers by meaning
- Connecting Jensen–Shannon and Kullback–Leibler Divergences: A New Bound for Representation Learning (NeurIPS 2025 · similarity 0.88)
- New Insights and Perspectives on the Natural Gradient Method (JMLR 2020 · similarity 0.87)
- Improved Mutual Information Estimation (AAAI 2021 · similarity 0.87)
- Bayesian Optimization with Fisher Information Geometry: Gradient Bounds and Trust-Region Methods (NeurIPS 2026 · similarity 0.86)
- Mutual Information Estimation via $f$-Divergence and Data Derangements (NeurIPS 2024 · similarity 0.85)
- Symmetric Single Index Learning (ICLR 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.
