B
Bradley Sturt
Researcher at University of Illinois at Chicago
Publications - 9
Citations - 1268
Bradley Sturt is an academic researcher from University of Illinois at Chicago. The author has contributed to research in topics: Robust optimization & Optimization problem. The author has an hindex of 6, co-authored 9 publications receiving 945 citations. Previous affiliations of Bradley Sturt include University of Illinois at Urbana–Champaign & Massachusetts Institute of Technology.
Papers
More filters
Proceedings ArticleDOI
Personalized entity recommendation: a heterogeneous information network approach
Xiao Yu,Xiang Ren,Yizhou Sun,Quanquan Gu,Bradley Sturt,Urvashi Khandelwal,Brandon Norick,Jiawei Han +7 more
TL;DR: This paper proposes to combine heterogeneous relationship information for each user differently and aim to provide high-quality personalized recommendation results using user implicit feedback data and personalized recommendation models.
Journal ArticleDOI
The path most traveled: Travel demand estimation using big data resources
Jameson L. Toole,Serdar Çolak,Bradley Sturt,Lauren P. Alexander,Alexandre G. Evsukoff,Marta C. González +5 more
TL;DR: This work presents a flexible, modular, and computationally efficient software system that estimates multiple aspects of travel demand using call detail records from mobile phones in conjunction with open- and crowdsourced geospatial data, census records, and surveys.
Proceedings ArticleDOI
Recommendation in heterogeneous information networks with implicit user feedback
Xiao Yu,Xiang Ren,Yizhou Sun,Bradley Sturt,Urvashi Khandelwal,Quanquan Gu,Brandon Norick,Jiawei Han +7 more
TL;DR: This paper proposes to combine various relationship information from the network with user feedback to provide high quality recommendation results and uses meta-path-based latent features to represent the connectivity between users and items along different paths in the related information network.
Posted Content
Dynamic optimization with side information.
TL;DR: Through a novel measure concentration result for a class of machine learning methods, it is proved that the proposed approach is asymptotically optimal for multi-period stochastic programming with side information.
Posted Content
Two-stage sample robust optimization
TL;DR: This work proposes an approximation algorithm that combines the asymptotic optimality and scalability of the sample average approximation while simultaneously offering improved out-of-sample performance guarantees for sample robust optimization problems.