Adaptive Submodularity: A New Approach to Active Learning and Stochastic Optimization
نویسندگان
چکیده
Solving stochastic optimization problems under partial observability, where one needs to adaptively make decisions with uncertain outcomes, is a fundamental but notoriously difficult challenge. In this paper, we introduce the concept of adaptive submodularity, generalizing submodular set functions to adaptive policies. We prove that if a problem satisfies this property, a simple adaptive greedy algorithm is guaranteed to be competitive with the optimal policy. We illustrate the usefulness of the concept by giving several examples of adaptive submodular objectives arising in diverse applications including sensor placement, viral marketing and pool-based active learning. Proving adaptive submodularity for these problems allows us to recover existing results in these applications as special cases and leads to natural generalizations.
منابع مشابه
Adaptive Submodularity: Theory and Applications in Active Learning and Stochastic Optimization
Solving stochastic optimization problems under partial observability, where one needs to adaptively make decisions with uncertain outcomes, is a fundamental but notoriously difficult challenge. In this paper, we introduce the concept of adaptive submodularity, generalizing submodular set functions to adaptive policies. We prove that if a problem satisfies this property, a simple adaptive greedy...
متن کاملNear-optimal Batch Mode Active Learning and Adaptive Submodular Optimization
Active learning can lead to a dramatic reduction in labeling effort. However, in many practical implementations (such as crowdsourcing, surveys, high-throughput experimental design), it is preferable to query labels for batches of examples to be labelled in parallel. While several heuristics have been proposed for batch-mode active learning, little is known about their theoretical performance. ...
متن کاملAdaptive Stochastic Optimization: From Sets to Paths
Adaptive stochastic optimization (ASO) optimizes an objective function adaptively under uncertainty. It plays a crucial role in planning and learning under uncertainty, but is, unfortunately, computationally intractable in general. This paper introduces two conditions on the objective function, the marginal likelihood rate bound and the marginal likelihood bound, which, together with pointwise ...
متن کاملAdaptive Budget Allocation for Maximizing Influence of Advertisements
The budget allocation problem is an optimization problem arising from advertising planning. In the problem, an advertiser has limited budgets to allocate across media, and seeks to optimize the allocation such that the largest fraction of customers can be influenced. It is known that this problem admits a (1 1/e)-approximation algorithm. However, no previous studies on this problem considered a...
متن کاملBudgeted stream-based active learning via adaptive submodular maximization
Active learning enables us to reduce the annotation cost by adaptively selecting unlabeled instances to be labeled. For pool-based active learning, several effective methods with theoretical guarantees have been developed through maximizing some utility function satisfying adaptive submodularity. In contrast, there have been few methods for stream-based active learning based on adaptive submodu...
متن کامل