arXiv (All)
open access
One Rate Is Not Enough: Adaptive Anisotropic Learning Rates for LoRA Fine-Tuning
Low-rank adaptation (LoRA) has become the standard for parameter-efficient fine-tuning of large language models. Most LoRA variants follow a uniform-LR convention, applying a single global learning rate across every rank-one component of every adapter. We show that this convention overlooks substant
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
- EDGC: Entropy-driven Dynamic Gradient Compression for Efficient LLM Training#1143639
- Fairness Beyond a Single Run: Training-Seed Variability in Speech LLM Adaptation#1143943
- GPart: End-to-End Isometric Fine-Tuning via Global Parameter Partitioning#1156355
- Understanding LLM Parameter Update Sparsity through the Lens of Fisher#1131104
- Mitigating Post-Training Effects on Generative Diversity in Language Models#634924
Record · ID 973505
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