XAIENCE 2019

Session

Contributed talks 1

7 Nov 2019, 17:15

국제회의실 (International Conference Hall) (Seoul National University, College of Natural Sciences, Building 25-1)

Conveners

Contributed talks 1

• Yongdai Kim (Seoul National University)

Contribution list Timetable

8. On Casting Importance Weighted Autoencoder to an EM Algorithm to Learn Deep Generative Models

Dr Dongha Kim (Seoul National University)

07/11/2019, 17:15

We propose a new and general approach to learn deep generative models. Our approach is based on a new observation that the importance weighted autoencoders (IWAE) can be understood as a procedure of estimating the MLE with an EM algorithm. Utilizing this interpretation, we develop a new learning algorithm called importance weighted EM algorithm (IWEM). IWEM is an EM algorithm with...

9. Nonconvex Sparse Regularization For Deep Neural Networks and its Optimal Property

Mr Ilsang Ohn (Department of Statistics, Seoul National University)

07/11/2019, 17:30

Sparsity is a key ingredient in the success of learners both theoretically and computationally. This is also the case for deep neural networks (DNNs). A number of empirical observations show that sparse DNNs can dramatically reduce computation time and memory without appreciably harming prediction power. Furthermore, recent theoretical studies proved that DNN estimators with a certain sparsity...