Country
PragmaticallyLearningfromPedagogical DemonstrationsinMulti-GoalEnvironments
In many situations, a single demonstration may be correctly interpreted as demonstration ofavariety ofgoals -wecallthisgoalambiguity.
Adversarial
Quantile (and, more generally, KL) regret bounds, such as those achieved by NormalHedge (Chaudhuri, Freund, and Hsu 2009) and its variants, relax the goal of competing against the best individual expert to only competing against a majority of experts on adversarial data.
Factor Group-Sparse Regularization for Efficient Low-Rank Matrix Recovery
Jicong Fan, Lijun Ding, Yudong Chen, Madeleine Udell
This paper develops a new class of nonconvex regularizers for low-rank matrix recovery.
Minimizers of the Empirical Risk and Risk Monotonicity
Marco Loog, Tom Viering, Alexander Mey
Neural Information Processing Systems http://nips.cc/
