132 citations
- University of MichiganUS3 papers
- University of Southern MississippiUS3 papers
- Assumption CollegeUS2 papers
- Carnegie Mellon UniversityUS2 papers
- Fraunhofer Institute for Applied and Integrated SecurityDE2 papers
- Massachusetts Institute of TechnologyUS2 papers
- National Institute of Standards and TechnologyUS2 papers
- University of IowaUS2 papers
- University of WashingtonUS2 papers
- Aalto UniversityFI1 paper
- Brandeis UniversityUS1 paper
- Brookhaven National LaboratoryUS1 paper
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2019★ 1 cited
Potential-Based Advice for Stochastic Policy Learning
Baicen Xiao, Bhaskar Ramasubramanian, Andrew Clark +3
This paper augments the reward received by a reinforcement learning agent with potential functions in order to help the agent learn (possibly stochastic) optimal policies. We show…
cs.LG2019★ 3 cited
Predicting Urban Dispersal Events: A Two-Stage Framework through Deep Survival Analysis on Mobility Data
Amin Vahedian, Xun Zhou, Ling Tong +2
Urban dispersal events are processes where an unusually large number of people leave the same area in a short period. Early prediction of dispersal events is important in mitigatin…
cs.LG2017★ 4 cited
Climbing the Kaggle Leaderboard by Exploiting the Log-Loss Oracle
Jacob Whitehill
In the context of data-mining competitions (e.g., Kaggle, KDDCup, ILSVRC Challenge), we show how access to an oracle that reports a contestant's log-loss score on the test set can…