no code implementations • 7 Dec 2016 • Sergey Bartunov, Dmitry P. Vetrov
Despite recent advances, the remaining bottlenecks in deep generative models are necessity of extensive training and difficulties with generalization from small number of training examples.
no code implementations • NeurIPS 2015 • Alexander Kirillov, Dmytro Shlezinger, Dmitry P. Vetrov, Carsten Rother, Bogdan Savchynskyy
In this work we show that the joint inference of $M$ best diverse solutions can be formulated as a submodular energy minimization if the original MAP-inference problem is submodular, hence fast inference techniques can be used.