Research map / Label-efficient and robust learning / Self-supervised and contrastive
Understanding Representation Learnability of Nonlinear Self-Supervised Learning
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 nonlinear SSL rather than nonlinear supervised learning | Two-neuron nonlinear models · Toy data distribution | capture of hidden feature e2: 1-O(τ^3d^{-\frac{1}{2}}); O\left(1/d^{1.4}\right) | Helped |
| Initialize SSL weights with correct signs instead of requiring initialization near the local minimum | Nonlinear SSL · Toy data distribution | capture of hidden feature e2 | Helped |
| Relax the theoretical lower bound on τ to τ=3 | Nonlinear SSL · Toy data distribution | alignment of learned representation with e1 and e2 | Helped |
Closest papers by meaning
- Non-parametric Representation Learning with Kernels (AAAI 2024 · similarity 0.88)
- Self-supervised Representation Learning from Random Data Projectors (ICLR 2024 · similarity 0.87)
- Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation (ICLR 2024 · similarity 0.86)
- Clustering Properties of Self-Supervised Learning (ICML 2025 · similarity 0.86)
- Measuring Self-Supervised Representation Quality for Downstream Classification Using Discriminative Features (AAAI 2024 · similarity 0.85)
- On the Importance of Embedding Norms in Self-Supervised Learning (ICML 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.