k-Support and Ordered Weighted Sparsity for Overlapping Groups: Hardness and Algorithms
–Neural Information Processing Systems
We study the norms obtained from extending the k-support norm and OWL norms to the setting in which there are overlapping groups. The resulting norms are in general NP-hard to compute, but they are tractable for certain collections of groups. To demonstrate this fact, we develop a dynamic program for the problem of projecting onto the set of vectors supported by a fixed number of groups.
Neural Information Processing Systems
Oct-2-2024, 19:34:31 GMT
- Country:
- North America > United States > New York > New York County > New York City (0.14)
- Technology: