Optimisation of Overparametrized Sum-Product Networks

05/20/2019 ∙ by Martin Trapp, et al. ∙ 0

It seems to be a pearl of conventional wisdom that parameter learning in deep sum-product networks is surprisingly fast compared to shallow mixture models. This paper examines the effects of overparameterization in sum-product networks on the speed of parameter optimisation. Using theoretical analysis and empirical experiments, we show that deep sum-product networks exhibit an implicit acceleration compared to their shallow counterpart. In fact, gradient-based optimisation in deep sum-product networks is equal to gradient ascend with adaptive and time-varying learning rates and additional momentum terms.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.