DynamicSasvi: StrongSafeScreeningfor Norm-RegularizedLeastSquares
–Neural Information Processing Systems
In this paper, we first propose a flexible framework for safe screening based on the Fenchel-Rockafellar duality and then deriveastrong safe screening rule for norm-regularized least squares using the proposed framework.
Neural Information Processing Systems
Feb-9-2026, 11:45:31 GMT
- Technology: