arXiv (OAI Expanded)
open access
Optimal Learning Rate Schedules under Functional Scaling Laws: Power Decay and Warmup-Stable-Decay
We study optimal learning rate (LR) schedules under the functional scaling law (FSL) framework (Li et al., 2025), which decomposes training dynamics into signal learning and noise forgetting. In power-law kernel regression, these two components are governed by a source exponent $s>0$ and a capacity
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
- When the Preconditioning Exponent Turns Negative: Learning-Rate Coupling and Cross-Environment Generalization#1104470
- Special Properties of Gradient Descent with Large Learning Rates#291939
- Continuous Optimization for p-adic Models#1061140
- Emergent One-Third Scaling Law as Attention Tries to Concentrate#1116431
- Model-free Learning with Heterogeneous Dynamical Systems: A Federated LQR Approach#1116050
Record · ID 1109783
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