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:
- Asia > Middle East
- Lebanon (0.04)
- Europe
- Denmark > Central Jutland
- Aarhus (0.04)
- Spain > Canary Islands (0.04)
- Denmark > Central Jutland
- North America > United States
- California > Los Angeles County
- Long Beach (0.04)
- Florida > Broward County
- Fort Lauderdale (0.04)
- New York > New York County
- New York City (0.14)
- Wisconsin > Dane County
- Madison (0.04)
- California > Los Angeles County
- Asia > Middle East
- Technology: