Research map / Learning theory and algorithms / Combinatorial and search optimization
Learning (from) Deep Hierarchical Structure among Features
Yu Zhang, Lei Han
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 |
|---|---|---|---|
| deeper hierarchy (DHS) instead of Lasso | sparse linear model · synthetic m = 5 | MSE: 1.8660 -> 1.4682 | Improved |
| learn the hierarchy (LDHS) instead of given hierarchy (DHS) | DHS · synthetic m = 3 | MSE: 0.2743 -> 0.2370 | Improved |
| learn the hierarchy (LDHS) instead of given hierarchy (DHS) | DHS · synthetic m = 4 | MSE: 0.8275 -> 0.8283 | No clear effect |
| learn the hierarchy (LDHS) instead of given hierarchy (DHS) | DHS · synthetic m = 5 | MSE: 1.4682 -> 1.3894 | Improved |
| deep hierarchy (DHS) instead of height-2 HP | HP · synthetic m = 5 | MSE: 1.5519 -> 1.4682 | Improved |
| DHSe variant instead of DHS | DHS · synthetic m = 5 | MSE: 1.4682 -> 1.5596 | Hurt |
| LDHS instead of HP | HP · Traffic Volume Task 1 | MSE: 0.0869 -> 0.0838 | Improved |
| LDHS instead of Lasso | Lasso · Traffic Volume Task 5 | MSE: 0.1632 -> 0.1373 | Improved |
| LDHS instead of DHS | DHS · Traffic Volume Task 3 | MSE: 0.0929 -> 0.0928 | No clear effect |
| DHSe instead of Lasso | Lasso · Breast Cancer | ACC (%): 76.81 -> 83.49 | Improved |
| DHSe instead of CAPℓ4 | CAPℓ4 · Breast Cancer | ACC (%): 81.53 -> 83.49 | Improved |
| DHS instead of CAPℓ4 | CAPℓ4 · Breast Cancer | SEN (%): 95.47 -> 91.59 | Hurt |
Closest papers by meaning
- How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model (ICML 2024 · similarity 0.87)
- The Computational Advantage of Depth in Learning High-Dimensional Hierarchical Targets (NeurIPS 2025 · similarity 0.86)
- Learning Structured Representations with Hyperbolic Embeddings (NeurIPS 2024 · similarity 0.83)
- From Logits to Hierarchies: Hierarchical Clustering made Simple (ICML 2025 · similarity 0.83)
- Improving Visual Recognition with Hyperbolical Visual Hierarchy Mapping (CVPR 2024 · similarity 0.83)
- Investigating the Overlooked Hessian Structure: From CNNs to LLMs (ICML 2025 · similarity 0.82)
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.
