Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed
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 |
|---|---|---|---|
| Train a small 2LNN with feature learning rather than use random features | Gaussian mixture classification · XOR-like Gaussian mixture, low SNR | classification error | Helped |
| Train a small 2LNN with feature learning rather than use random features | Gaussian mixture classification · XOR-like Gaussian mixture, mixed SNR | generalisation error | Helped |
| Use random features rather than a small 2LNN | Gaussian mixture classification · XOR-like Gaussian mixture, high SNR | classification error | No clear effect |
| Increase L2 regularisation (ablation) | 2LNN · XOR-like Gaussian mixture | test error | Hurt |
| Add neurons beyond the 4 needed to reach oracle-like performance (ablation) | 2LNN · XOR-like Gaussian mixture | classification error | No clear effect |
| Add neurons beyond the 4 needed to reach oracle-like performance (ablation) | 2LNN · XOR-like Gaussian mixture | fraction converging to optimal solution | Helped |
Closest papers by meaning
- Asymptotic Analysis of Two-Layer Neural Networks after One Gradient Step under Gaussian Mixtures Data with Structure (ICLR 2025 · similarity 0.91)
- Mean-field Analysis on Two-layer Neural Networks from a Kernel Perspective (ICML 2024 · similarity 0.88)
- From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning (ICML 2025 · similarity 0.87)
- Asymptotics of feature learning in two-layer networks after one gradient-step (ICML 2024 · similarity 0.86)
- Three Mechanisms of Feature Learning in a Linear Network (ICLR 2025 · similarity 0.86)
- Is Kernel Prediction More Powerful than Gating in Convolutional Neural Networks? (ICML 2024 · similarity 0.86)
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.