Research map / Probabilistic and scientific modeling / Molecules and proteins
Manifold Structured Prediction
Alessandro Rudi, Carlo Ciliberto, GianMaria Marconi, Lorenzo Rosasco
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 manifold structured prediction instead of KRLS | PD inverse prediction · PD inverse, dimensions 5–30 | squared geodesic loss: 111 (64) vs 0.94 (0.06); 44 (8.3) vs 1.24 (0.06); 56 (10) vs 1.25 (0.05); 59 (12) vs 1.33 (0.03); 72 (9) vs 1.44 (0.03); | Improved |
| Use manifold structured prediction instead of KRLS | PD inverse prediction · PD inverse, dimensions 5–30 | squared loss: 0.72 (0.08) vs 0.89 (0.08); 0.81 (0.03) vs 0.92 (0.05); 0.83 (0.03) vs 0.91 (0.06); 0.85 (0.02) vs 0.91 (0.03); 0.87 (0. | Mixed |
| Use manifold structured prediction instead of KRLS | Multilabel prediction · Emotions | AUC: 0.63 -> 0.73 | Improved |
| Use manifold structured prediction instead of KRLS | Multilabel prediction · CAL500 | AUC: 0.92 -> 0.92 | No clear effect |
| Use manifold structured prediction instead of KRLS | Multilabel prediction · Scene | AUC: 0.62 -> 0.73 | Improved |
| Use manifold structured prediction instead of KRLS | Fingerprint contour reconstruction · Single fingerprint image | average absolute error (degrees): 25.3 -> 15.7 | Improved |
| Use manifold structured prediction instead of manifold regression | Fingerprint contour reconstruction · FVC fingerprint verification challenge | average absolute error (degrees) | Improved |
Closest papers by meaning
- A General Framework for Consistent Structured Prediction with Implicit Loss Embeddings (JMLR 2020 · similarity 0.91)
- Sample complexity and effective dimension for regression on manifolds (NeurIPS 2020 · similarity 0.88)
- A Consistent Regularization Approach for Structured Prediction (NeurIPS 2016 · similarity 0.86)
- Conformal Structured Prediction (ICLR 2025 · similarity 0.85)
- Hardness of Learning Neural Networks under the Manifold Hypothesis (NeurIPS 2024 · similarity 0.84)
- Curvature Enhanced Data Augmentation for Regression (ICML 2025 · 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.
