arXiv (All)
open access
A "feature ODE" describing the learning behavior of shallow MLPs on simple functions
We study the gradient flow training dynamics of two-layer multi-layer perceptrons (MLPs) on anisotropic Gaussian data. Even in this simple setting, solving the dynamics in full is notoriously difficult, so we try something different. We propose a "feature ODE" that might be intuitively expected to d
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Unifying Graph Neural Networks Through a Common Layer Equation#620512
- Unifying Graph Neural Networks Through a Common Layer Equation#618833
- On Parameter Symmetries and Conservation Laws in Gradient Flow#1128814
- From the Loss Landscape to Diverse Feature Learning in Neural Networks#793177
- From the Loss Landscape to Diverse Feature Learning in Neural Networks#789173
Record · ID 1400474
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive