AI RESEARCH
Memory-Efficient Structured Backpropagation for On-Device LLM Fine-Tuning
arXiv CS.LG
•
ArXi:2602.13069v2 Announce Type: replace On-device fine-tuning enables privacy-preserving personalization of large language models, but mobile devices impose severe memory constraints, typically 6--12GB shared across all workloads. Existing approaches force a trade-off between exact gradients with high memory (MeBP) and low memory with noisy estimates (MeZO). We propose Memory-efficient Structured Backpropagation (MeSP), which bridges this gap by manually deriving backward passes that exploit LoRA's low-rank structure.