arXiv (All)
open access
Global Exponential Convergence of Two-Layer Linear Network Training
We prove global exponential (linear) convergence with an explicit rate in the rich scaling for wide two-layer linear networks trained with smooth Polyak-Lojasiewicz predictor losses. Gradient flow in the factors closes exactly in terms of a finite-dimensional Bures flow of the neuron law covariance,
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
- A lift for input-convex neural net training#1062907
- A prism hierarchy of learning regimes in large linear autoencoders#1232762
- On the Decompositionality of Neural Networks#2676
- Let the Neurons Die: Exploiting ReLU-Induced Model Degradation#1130109
- Let the Neurons Die: Exploiting ReLU-Induced Model Degradation#1108784
Record · ID 1233395
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