Research map / Label-efficient and robust learning / Self-supervised and contrastive
Predicting What You Already Know Helps: Provable Self-Supervised Learning
Jason D. Lee, Qi Lei, Nikunj Saunshi, Jiacheng Zhuo
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 |
|---|---|---|---|
| learn linear predictor on inpainting representation psi instead of directly on X1 or X2 | linear model, Yearbook · Yearbook date regression | MSE | Improved |
| learn ResNet18 on inpainting representation psi instead of on X1 | ResNet18, Yearbook · Yearbook date regression (limited labels) | MSE | Improved |
| increase k (label cardinality) in synthetic mixture of Gaussians | SSL linear representation · Synthetic Gaussian mixtures | MSE | Hurt |
| increase approximate conditional independence violation epsilon_CI | SSL linear representation · Synthetic Gaussian mixtures | MSE | Hurt |
Closest papers by meaning
- Self-supervised Learning from a Multi-view Perspective (ICLR 2021 · similarity 0.87)
- Self-Supervised Learning of Pretext-Invariant Representations (CVPR 2020 · similarity 0.87)
- Rethinking Minimal Sufficient Representation in Contrastive Learning (CVPR 2022 · similarity 0.86)
- On Discriminative Probabilistic Modeling for Self-Supervised Representation Learning (ICLR 2025 · similarity 0.86)
- Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks (ICML 2024 · similarity 0.85)
- Provable Sample-Efficient Transfer Learning Conditional Diffusion Models via Representation Learning (NeurIPS 2025 · similarity 0.85)
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.
