Research map / Learning theory and algorithms / Matrix and tensor methods
Scalable and Adaptive Trust-Region Learning via Projection Convex Hull
Hongyang Jia, Qingchun Hou, Bojun Du, Xiao Cai, Ning Zhang, Chongqing Kang
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 PCH instead of CGHC | CGHC · PH 15 100 | trust-region accuracy (%): 57.20 -> 99.95 | Improved |
| use PCH instead of PinCHD | PinCHD · NLC N 100 | trust-region accuracy (%): 53.75 -> 99.01 | Improved |
| use PCH instead of DeepHull | DeepHull · PH 15 100 | trust-region accuracy (%): 64.39 -> 99.95 | Improved |
| use PCH instead of PinCHD | PinCHD · PH 15 100 | number of hyperplanes: 1499 -> 15 | Improved |
| use PCH instead of QH on low-dim nonconvex data | QH · NLNC N 2 | trust-region accuracy (%): 92.15 -> 92.10 | No clear effect |
| use PCH instead of CGHC | CGHC · Spambase | trust-region accuracy (%): 86.70 -> 94.41 | Improved |
| use PCH instead of DeepHull | DeepHull · HIV | trust-region accuracy (%): 99.55 -> 99.94 | Improved |
| add PCH trust-region filtering at inference | CART classifier · spambase | classification accuracy (%): 91.10 -> 93.27 | Improved |
| retrain classifier on PCH trust region samples | CART classifier · NLNC N 2 | classification accuracy (%): 98.30 -> 99.00 | Improved |
| add PCH† filtering to MLP constraint learning | MLP constraint learner · Constraint learning | feasibility rate (%): 88% to 94% | Improved |
| add PCH† filtering to MLP constraint learning | MLP constraint learner · Constraint learning | binary variables: 205 to 35 | Improved |
Closest papers by meaning
- TRAM: Bridging Trust Regions and Sharpness Aware Minimization (ICLR 2024 · similarity 0.85)
- Regional Expected Improvement for Efficient Trust Region Selection in High-Dimensional Bayesian Optimization (AAAI 2025 · similarity 0.85)
- Trust Region Methods for Nonconvex Stochastic Optimization beyond Lipschitz Smoothness (AAAI 2024 · similarity 0.84)
- Navigating Conflicting Views: Harnessing Trust for Learning (ICML 2025 · similarity 0.83)
- Bayesian Optimization with Fisher Information Geometry: Gradient Bounds and Trust-Region Methods (NeurIPS 2026 · similarity 0.83)
- Angular Constraint Embedding via SpherePair Loss for Constrained Clustering (NeurIPS 2025 · similarity 0.83)
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.
