Research map / Learning theory and algorithms / Prediction and decision losses
Split LBI: An Iterative Regularization Path with Structural Sparsity
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 |
|---|---|---|---|
| increase nu from 1 to 5 (ablation) | Split LBI · Standard Lasso | mean AUC: .9845 -> .9969 | Helped |
| increase nu from 5 to 10 (ablation) | Split LBI · Standard Lasso | mean AUC: .9969 -> .9982 | Helped |
| increase nu from 1 to 5 (ablation) | Split LBI · 1-D fused Lasso | mean AUC: .9955 -> .9996 | Helped |
| increase nu from 5 to 10 (ablation) | Split LBI · 1-D fused Lasso | mean AUC: .9996 -> .9998 | Helped |
| replace genlasso with Split LBI (nu=1) | Split LBI · Standard Lasso | mean AUC: .9426 -> .9845 | Helped |
| replace genlasso with Split LBI (nu=10) | Split LBI · Standard Lasso | mean AUC: .9426 -> .9982 | Helped |
| replace genlasso with Split LBI (nu=1) | Split LBI · 1-D fused Lasso | mean AUC: .9705 -> .9955 | Helped |
| replace genlasso with Split LBI (nu=10) | Split LBI · 1-D fused Lasso | mean AUC: .9705 -> .9998 | Helped |
| increase nu in 1 to 300 range (ablation) | Split LBI · Image denoising (red channel) | mean AUC | Helped |
| increase nu (std of AUC shrinks) | Split LBI · Standard Lasso | mean AUC: (.0390) -> (.0043) | Helped |
Closest papers by meaning
- An Alternating Proximal Splitting Method with Global Convergence for Nonconvex Structured Sparsity Optimization (AAAI 2016 · similarity 0.88)
- A Matrix Splitting Method for Composite Function Minimization (CVPR 2017 · similarity 0.86)
- Iterative Regularization with k-support Norm: An Important Complement to Sparse Recovery (AAAI 2024 · similarity 0.86)
- MAP Estimation with Denoisers: Convergence Rates and Guarantees (NeurIPS 2025 · similarity 0.84)
- Weakly Convex Regularisers for Inverse Problems: Convergence of Critical Points and Primal-Dual Optimisation (ICML 2024 · similarity 0.84)
- SequentialAttention++ for Block Sparsification: Differentiable Pruning Meets Combinatorial Optimization (NeurIPS 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.