arXiv (All)
open access
Efficient Pre-Training of LLMs through Truncated SVD Representations
LLM pretraining is extremely costly; therefore, parameter-efficient LLM architectures have recently emerged as a compelling research direction. One such promising approach is to represent the parameters as orthonormal low-rank weight matrices. However, maintaining orthonormality during training is c
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
- Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing#204779
- AMO: Operator-level Adaptive Muon Orthogonalization#1117421
- GRACE:Gradient-guided Coreset Selection for LLM Unlearning#618564
- Projected Riemannian Gradient Descent for the Bures-Wasserstein Barycenter: Dimension-Independent Linear Convergence at Unit Step Size#926649
- Bilinear Optimization Divergence: Diagnosing Factor-Constrained LoRA Continual Learning#1049333
Record · ID 1141553
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