Unverified50% confidenceFactExact time
LoRA (Low-Rank Adaptation) constrains the weight update matrix ΔW to BA via low-rank decomposition, where B∈ℝ^{d×r}, A∈ℝ^{r×k}, and rank r≪min(d,k), thereby reducing the number of trainable parameters from d×k to r×(d+k).
1
Sources
50%
Confidence
Long-term
Relevance
10/24/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedLoRA attaches two low-rank matrices A and B in parallel alongside each target weight matrix, where A is randomly initialized and B is initialized to zero; only these two small matrices are trained, and during inference the product A×B is added back to the original weights.75% similarUnverifiedLoRA 由 Hu 等人在 2021 年提出，通过为每层注入可训练的低秩分解矩阵实现参数更新 ΔW = BA，将可训练参数量压缩至原始模型的 0.1%-1%74% similarVerifiedLoRA achieves fine-tuning by inserting low-rank decomposition matrices alongside the model's weight matrices, typically requiring training of only 0.1%–1% of the original parameter count.74% similarVerifiedThe principle of LoRA is to decompose the weight change ΔW during fine-tuning into the product of two low-rank matrices (ΔW = A×B).74% similarUnverifiedIn LoRA's scaling factor α/r, dividing by r serves a normalization purpose, so that adjusting r does not require a simultaneous adjustment of the learning rate.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1093829API
curl https://kongchang.com/api/v1/knowledge/claims/1093829MCP
get_claim(id=1093829)