Research map / Learning theory and algorithms / Sample complexity
Multi-step learning and underlying structure in statistical 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 |
|---|---|---|---|
| Multi-step (unsupervised-then-supervised, e.g. learning invariant or manifold features first) approach versus single-step purely supervised learner | Manifold learning example (union of N linear segments) and group-invariant feature example · Theoretical analysis (minimax sample complexity lower/upper bounds) | worst-case expected error / sample complexity | Helped |
| Gap between learner with oracle knowledge of intermediate representation t and learner without it (multi-step with learned structure) | Manifold learning example · Theoretical analysis | worst-case expected error lower bound | Hurt |
Closest papers by meaning
- A Trichotomy for List Transductive Online Learning (ICML 2025 · similarity 0.81)
- Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuse (NeurIPS 2024 · similarity 0.81)
- CGMatch: A Different Perspective of Semi-supervised Learning (CVPR 2025 · similarity 0.81)
- Surprises in Proper Positive-Only Learning (NeurIPS 2026 · similarity 0.81)
- Scores for Learning Discrete Causal Graphs with Unobserved Confounders (AAAI 2024 · similarity 0.81)
- Transfer Learning of Linear Regression with Multiple Pretrained Models: Benefiting from More Pretrained Models via Overparameterization Debiasing (NeurIPS 2026 · similarity 0.80)
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.