GAP Safe Screening Rules for Sparse-Group-Lasso
This work addresses computational bottlenecks for researchers and practitioners using Sparse-Group Lasso in high-dimensional data analysis, though it is incremental as it adapts existing screening rules to a specific model.
The paper tackled the problem of improving computational efficiency for Sparse-Group Lasso in high-dimensional settings by developing new safe screening rules that discard irrelevant features or groups early, resulting in significant gains in computing time for a coordinate descent implementation.
In high dimensional settings, sparse structures are crucial for efficiency, either in term of memory, computation or performance. In some contexts, it is natural to handle more refined structures than pure sparsity, such as for instance group sparsity. Sparse-Group Lasso has recently been introduced in the context of linear regression to enforce sparsity both at the feature level and at the group level. We adapt to the case of Sparse-Group Lasso recent safe screening rules that discard early in the solver irrelevant features/groups. Such rules have led to important speed-ups for a wide range of iterative methods. Thanks to dual gap computations, we provide new safe screening rules for Sparse-Group Lasso and show significant gains in term of computing time for a coordinate descent implementation.