paper-with-me

Papers

Learning Policies for Contextual Submodular Prediction

2013-05-11 · Stephane Ross, Jiaji Zhou, Yisong Yue, Debadeepta Dey, J. Andrew Bagnell

Many prediction domains, such as ad placement, recommendation, trajectory prediction, and document summarization, require predicting a set or list of options. Such lists are often evaluated using submodular reward functions that measure both quality and diversity. We propose a simple, efficient, and provably near-optimal approach to optimizing such prediction problems based on no-regret learning. Our method leverages a surprising result from online submodular optimization: a single no-regret online learner can compete with an optimal sequence of predictions. Compared to previous work, which either learn a sequence of classifiers or rely on stronger assumptions such as realizability, we ensure both data-efficiency as well as performance guarantees in the fully agnostic setting. Experiments validate the efficiency and applicability of the approach on a wide range of problems including manipulator trajectory optimization, news recommendation and document summarization.

📄 PDF Abstract BibTeX arXiv:1305.2532

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityDocument SummarizationNews RecommendationPredictionTrajectory Prediction

Similar Papers 제목 키워드 기반

Knapsack Constrained Contextual Submodular List Prediction with Application to Multi-document Summarization

2013-08-16 · Jiaji Zhou, Stephane Ross, Yisong Yue, Debadeepta Dey 외

We study the problem of predicting a set or list of options under knapsack constraint. The quality of such lists are evaluated by a submodular reward function that measures both quality and diversity. Similar to DAgger (…

DiversityDocument SummarizationMulti-Document Summarization

Online Submodular Set Cover, Ranking, and Repeated Active Learning

2011-12-01 · NeurIPS 2011 12 · Andrew Guillory, Jeff A. Bilmes

We propose an online prediction version of submodular set cover with connections to ranking and repeated active learning. In each round, the learning algorithm chooses a sequence of items. The algorithm then receives a…

Active Learning

Contextual Combinatorial Multi-armed Bandits with Volatile Arms and Submodular Reward

2018-12-01 · NeurIPS 2018 12 · Lixing Chen, Jie Xu, Zhuo Lu

In this paper, we study the stochastic contextual combinatorial multi-armed bandit (CC-MAB) framework that is tailored for volatile arms and submodular reward functions. CC-MAB inherits properties from both contextual ba…

Decision MakingMulti-Armed BanditsRecommendation Systems

Adaptive Submodularity: Theory and Applications in Active Learning and Stochastic Optimization

2010-03-21 · Daniel Golovin, Andreas Krause

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 introduc…

Active LearningMarketingStochastic Optimization

Online Submodular Maximization via Online Convex Optimization

2023-09-08 · Tareq Si Salem, Gözde Özcan, Iasonas Nikolaou, Evimaria Terzi 외

We study monotone submodular maximization under general matroid constraints in the online setting. We prove that online optimization of a large class of submodular functions, namely, weighted threshold potential function…