3 NeurIPS

Learning to Transfer Initializations for Bayesian Hyperparameter Optimization

NeurIPS 2017 Workshop on Bayesian Optimization Learning to Transfer Initializations for Bayesian Hyperparameter OptimizationJungtaek Kim, Saehoon Kim, Seungjin Choi We propose a neural network to learn meta-features over datasets, which is used to select initial points for Bayesian hyperpa...

2 ICML

Graphical Models for Ordinal Data: A Tale of Two Approaches

ICML 2017 Graphical Models for Ordinal Data: A Tale of Two ApproachesArun Sai Suggala, Eunho Yang, P. Ravikumar Undirected graphical models or Markov random fields (MRFs) are widely used for modeling multivariate probability distributions. Much of the work on MRFs has focused on continuous...

1 ICML

Combined Group and Exclusive Sparsity for Deep Neural Networks

ICML 2017 Combined Group and Exclusive Sparsity for Deep Neural NetworksJaehong Yoon, SungJu Hwang The number of parameters in a deep neural network is usually very large, which helps with its learning capacity but also hinders its scalability and practicality due to memory/time inefficien...