Adaptive Submodular Meta-Learning
This work provides a computationally efficient approach for adaptive item selection under uncertainty, relevant for practitioners dealing with dynamic, state-dependent optimization problems.
This paper addresses adaptive submodular meta-learning where item states are initially unknown and must be observed by selection. The goal is to adaptively select an item group for optimal performance across tasks, achieving a 1/2 approximation ratio for monotone cases and 1/32 for non-monotone cases.
Meta-Learning has gained increasing attention in the machine learning and artificial intelligence communities. In this paper, we introduce and study an adaptive submodular meta-learning problem. The input of our problem is a set of items, where each item has a random state which is initially unknown. The only way to observe an item's state is to select that item. Our objective is to adaptively select a group of items that achieve the best performance over a set of tasks, where each task is represented as an adaptive submodular function that maps sets of items and their states to a real number. To reduce the computational cost while maintaining a personalized solution for each future task, we first select an initial solution set based on previously observed tasks, then adaptively add the remaining items to the initial solution set when a new task arrives. As compared to the solution where a brand new solution is computed for each new task, our meta-learning based approach leads to lower computational overhead at test time since the initial solution set is pre-computed in the training stage. To solve this problem, we propose a two-phase greedy policy and show that it achieves a $1/2$ approximation ratio for the monotone case. For the non-monotone case, we develop a two-phase randomized greedy policy that achieves a $1/32$ approximation ratio.