Efficient Symmetric Norm Regression via Linear Sketching
Zhao Song, Ruosong Wang, Lin Yang, Hongyang Zhang, Peilin Zhong
–Neural Information Processing Systems
We provide efficient algorithms for overconstrained linear regression problems with size n d when the loss function is a symmetric norm (a norm invariant under sign-flips and coordinate-permutations).
Neural Information Processing Systems
Jan-25-2025, 01:31:24 GMT