Negative Dependence: Theory and Applications in Machine Learning
Mike Gartrell · Jennifer Gillenwater · Alex Kulesza · Zelda Mariet

Fri Jun 14th 08:30 AM -- 06:00 PM @ 204
Event URL: »

Models of negative dependence are increasingly important in machine learning. Whether selecting training data, finding an optimal experimental design, exploring in reinforcement learning, or making suggestions with recommender systems, selecting high-quality but diverse items has become a core challenge. This workshop aims to bring together researchers who, using theoretical or applied techniques, leverage negative dependence in their work. We will delve into the rich underlying mathematical theory, understand key applications, and discuss the most promising directions for future research.

08:45 AM Opening Remarks (-) Video » 
08:50 AM Victor-Emmanuel Brunel: Negative Association and Discrete Determinantal Point Processes (Invited talk) Video »  Victor-Emmanuel Brunel
09:30 AM Aarti Singh: Experimental Design (Invited talk) Aarti Singh
10:10 AM On Two Ways to use Determinantal Point Processes for Monte Carlo Integration (Contributed talk) Video »  Guillaume Gautier
10:30 AM [Coffee Break] (Break)
11:00 AM Jeff Bilmes: Deep Submodular Synergies (Invited Talk) Video »  Jeff Bilmes
11:40 AM Submodular Batch Selection for Training Deep Neural Networks (Contributed Talk) Video »  Vineeth N Balasubramanian
12:00 PM [Lunch Break] (Break)
02:00 PM Michal Valko: How Negative Dependence Broke the Quadratic Barrier for Learning with Graphs and Kernels (Invited Talk) Video »  Michal Valko
02:40 PM Exact Sampling of Determinantal Point Processes with Sublinear Time Preprocessing (Contributed Talk) Video »  Michal Derezinski
03:00 PM [Coffee Break] (Break)
03:30 PM Sergei Levine: Distribution Matching and Mutual Information in Reinforcement Learning (Invited Talk) Video »  Sergey Levine
04:10 PM Seq2Slate: Re-ranking and Slate Optimization with RNNs (Contributed Talk) Video »  Ofer Meshi
04:30 PM [Mini Break] (Break)
04:40 PM Cheng Zhang: Active Mini-Batch Sampling using Repulsive Point Processes (Invited Talk) Video »  Cheng Zhang
05:20 PM Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret (Contributed Talk) Video »  Michal Valko
05:40 PM Towards Efficient Evaluation of Risk via Herding (Contributed Talk) Zelai Xu
06:00 PM Closing Remarks (-)

Author Information

Mike Gartrell (Criteo AI Lab)
Jennifer Gillenwater (Google Research NYC)
Alex Kulesza (Google)
Zelda Mariet (Massachusetts Institute of Technology)

More from the Same Authors