Unverified50% confidenceFactExact time
For a d×d weight matrix, LoRA decomposes it into two low-rank matrices A (d×r) and B (r×d), reducing trainable parameters from d² to 2dr, where the rank r is typically 8, 16 or 64.
1
Sources
50%
Confidence
Long-term
Relevance
10/28/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedLoRA decomposes the weight update matrix ΔW into the product of two small matrices A and B whose ranks are much lower than the original matrix, reducing parameter count to as little as one ten-thousandth of the original or even less.75% similarVerifiedLoRA将对权重矩阵的全量更新分解为两个低秩矩阵的乘积，训练时只更新这两个小矩阵，原始权重保持冻结74% similarUnverifiedLoRA leverages the low-rank approximation principle of SVD to decompose the incremental updates of large weight matrices into the product of two low-rank matrices, thereby compressing the number of trainable parameters from billions to the millions range.73% similarUnverifiedLoRA expresses the weight update as ΔW = BA, where B and A are low-rank matrices and the rank r is much smaller than min(d,k); during training only A and B are updated while the original model parameters are frozen.72% similarUnverifiedLow-rank parameterization decomposes the covariance matrix into a low-rank factor plus a diagonal matrix form, reducing the parameter count from O(d²) to O(dr).69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1108781API
curl https://kongchang.com/api/v1/knowledge/claims/1108781MCP
get_claim(id=1108781)