Timezone: »

Adversarial Prediction Games for Multivariate Losses
Hong Wang · Wei Xing · Kaiser Asif · Brian Ziebart

Mon Dec 07 04:00 PM -- 08:59 PM (PST) @ 210 C #54

Multivariate loss functions are used to assess performance in many modern prediction tasks, including information retrieval and ranking applications. Convex approximations are typically optimized in their place to avoid NP-hard empirical risk minimization problems. We propose to approximate the training data instead of the loss function by posing multivariate prediction as an adversarial game between a loss-minimizing prediction player and a loss-maximizing evaluation player constrained to match specified properties of training data. This avoids the non-convexity of empirical risk minimization, but game sizes are exponential in the number of predicted variables. We overcome this intractability using the double oracle constraint generation method. We demonstrate the efficiency and predictive performance of our approach on tasks evaluated using the precision at k, the F-score and the discounted cumulative gain.

Author Information

Hong Wang (University of Illinois at Chic)
Wei Xing (University of Illinois at Chicago)
Kaiser Asif (University of Illinois at Chicago)
Brian Ziebart (University of Illinois at Chicago)

More from the Same Authors