Research map / Learning theory and algorithms / Sample complexity
Contrastive Learning from Pairwise Measurements
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 dimension d from 5 to 20 (d in 5,10,15,20) | contrastive estimator, rank r=2 · Simulation, Bernoulli measurements | rescaled estimation error 1/d * ||Theta_hat - Theta*||_F vs 1/sqrt(n) | Hurt |
| increase rank r from 2 to 8 (r in 2,4,6,8) | contrastive estimator, d=20 · Simulation, Bernoulli measurements | rescaled estimation error 1/d * ||Theta_hat - Theta*||_F vs 1/sqrt(n) | Hurt |
| increase sample size n from 200 to 3000 | contrastive estimator · Simulation, Bernoulli measurements, various (r,d) | rescaled estimation error | Helped |
Closest papers by meaning
- Statistical Consistency and Generalization of Contrastive Representation Learning (ICML 2026 · similarity 0.85)
- Understanding Contrastive Learning via Gaussian Mixture Models (NeurIPS 2025 · similarity 0.85)
- Embedding Dimension of Contrastive Learning and $k$-Nearest Neighbors (NeurIPS 2024 · similarity 0.85)
- Near-Optimality of Contrastive Divergence Algorithms (NeurIPS 2024 · similarity 0.84)
- On the Similarities of Embeddings in Contrastive Learning (ICML 2025 · similarity 0.84)
- A Statistical Theory of Contrastive Learning via Approximate Sufficient Statistics (NeurIPS 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.