Research map / Learning theory and algorithms / Prediction and decision losses
On Learning High Dimensional Structured Single Index Models
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 |
|---|---|---|---|
| Use CSI instead of the strongest listed baseline | Sparse SIM classification · link | AUC: 0.976 -> 0.981 | Helped |
| Use CSI instead of the strongest listed baseline | Sparse SIM classification · page | AUC: 0.999 -> 0.997 | Hurt |
| Use CSI instead of the strongest listed baseline | Sparse SIM classification · ath-rel | AUC: 0.875 -> 0.879 | Helped |
| Use CSI instead of the strongest listed baseline | Sparse SIM classification · aut-mot | AUC: 0.923 -> 0.941 | Helped |
| Use CSI instead of the strongest listed baseline | Sparse SIM classification · cryp-ele | AUC: 0.994 -> 0.990 | Hurt |
| Use CSI instead of the strongest listed baseline | Sparse SIM classification · mac-win | AUC: 0.649 -> 0.646 | Hurt |
| Use CSI with group-sparsity constraints instead of linear regression | Group-sparse multitask regression · atp7d | MSE: 0.8198 -> 0.0611 | Helped |
| Use CSI with group-sparsity constraints instead of logistic regression | Group-sparse multilabel classification · Flags | F1: 0.6458 -> 0.6539 | Helped |
| Replace least-squares loss with the calibrated SIM loss | Structured matrix factorization · Epinions | MSE: 1.0012 -> 0.9488 | Helped |
| Replace least-squares loss with the calibrated SIM loss | Structured matrix factorization · Flixster | MSE: 1.0065 -> 0.9823 | Helped |
Closest papers by meaning
- Sample and Computationally Efficient Robust Learning of Gaussian Single-Index Models (NeurIPS 2024 · similarity 0.88)
- Learning Low-dimensional Latent Dynamics from High-dimensional Observations: Non-asymptotics and Lower Bounds (ICML 2024 · similarity 0.86)
- Robust group and simultaneous inferences for high-dimensional single index model (NeurIPS 2024 · similarity 0.86)
- Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model (ICLR 2025 · similarity 0.85)
- Learning single index models via harmonic decomposition (NeurIPS 2025 · similarity 0.85)
- Robustly Learning Single-Index Models via Alignment Sharpness (ICML 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.