Constrained Robust Submodular Partitioning

In the robust submodular partitioning problem, we aim to allocate a set of items into m blocks, so that the evaluation of the minimum block according to a submodular function is maximized. Robust submodular partitioning promotes the diversity of every block in the partition. It has many applications in machine learning, e.g., partitioning data for distributed training so that the gradients computed on every block are consistent. We study an extension of the robust submodular partition problem with additional constraints (e.g., cardinality, multiple matroids, and/or knapsack) on every block. For example, when partitioning data for distributed training, we can add a constraint that the number of samples of each class is the same in each partition block, ensuring data balance. We present two classes of algorithms, i.e., Min-Block Greedy based algorithms (with an ⌦(1/m) bound), and Round-Robin Greedy based algorithms (with a constant bound) and show that under various constraints, they still have good approximation guarantees. Interestingly, while normally the latter runs in only weakly polynomial time, we show that using the two together yields strongly polynomial running time while preserving the approximation guarantee. Lastly, we apply the algorithms on a real-world machine learning data partitioning problem showing good results. . Ghodsi et al. [11] proposes a local search algorithm with a bound of 1 3 . Both [3] and [11] requires guessing of the optimal solution value from an exponentially decreasing sequence of values, so strictly speaking, they lose an extra (1 + )-factor in the approxima-