Stochastic Continuous Greedy ++: When Upper and Lower Bounds Match
Amin Karbasi, Hamed Hassani, Aryan Mokhtari, Zebang Shen
–Neural Information Processing Systems
In this paper, we develop Stochastic Continuous Greedy++ (SCG++), the first efficient variant of a conditional gradient method for maximizing a continuous submodular function subject to a convex constraint.
Neural Information Processing Systems
Jan-23-2025, 08:08:03 GMT