We transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model th...
Contextual bandit learning is a reinforcement learning problem where the learner repeatedly receives a set of features (context), takes an action and receives a reward based on th...
We study the prevalent problem when a test distribution differs from the training distribution. We consider a setting where our training set consists of a small number of sample d...
Ruslan Salakhutdinov, Sham M. Kakade, Dean P. Fost...
Open-text semantic parsers are designed to interpret any statement in natural language by inferring a corresponding meaning representation (MR – a formal representation of its s...
Antoine Bordes, Xavier Glorot, Jason Weston, Yoshu...
We propose a new family of latent variable models called max-margin min-entropy (m3e) models, which define a distribution over the output and the hidden variables conditioned on ...
Kevin Miller, M. Pawan Kumar, Benjamin Packer, Dan...