Unverified50% confidenceFactExact time
Muon applies the matrix sign function to the SGD momentum gradient of weight matrices—performing SVD on the matrix and setting all singular values to 1—which is equivalent to finding the orthogonal matrix closest to the gradient matrix.
1
Sources
50%
Confidence
Long-term
Relevance
9/21/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe mathematical foundation of low-rank approximation comes from singular value decomposition (SVD) in linear algebra, which can approximate a matrix with a small effective rank using the product of two low-dimensional matrices U·V^T.77% similarUnverifiedSVD decomposes an arbitrary m×n matrix A into the form A=UΣVᵀ, where U and V are orthogonal matrices and Σ is a diagonal matrix, and the solution to the homogeneous equation Ah=0 is the last column of V.77% similarVerifiedSVD (Singular Value Decomposition) can decompose any matrix into the product of three matrices, and is the mathematical foundation of matrix factorization in recommender systems, image compression, and Latent Semantic Analysis (LSA).74% similarVerifiedSVD is the mathematical core of PCA dimensionality reduction, recommender system matrix factorization, and the LoRA low-rank adaptation fine-tuning method.68% similarUnverifiedSVD求解最经典的迭代算法是Golub-Kahan双对角化算法，大规模稀疏矩阵常用Lanczos算法或随机化SVD等近似方法68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/937867API
curl https://kongchang.com/api/v1/knowledge/claims/937867MCP
get_claim(id=937867)