Learning the Structure of Sum-Product Networks

By Robert Gens, Pedro M. Domingos. International Conference on Machine Learning, 2013

302 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Avoiding pathologies in very deep networks (2014, methodology): “Much recent work on deep networks has focused on weight initialization (Martens, 2010), regularization (Lee et al., 2007) and network architecture (Gens and Domingos, 2013).”
Online Algorithms for Sum-Product Networks with Continuous Variables (2016, unknown): “…algorithms for SPNs are generally based on clustering techniques that greedily construct a structure by partitioning/grouping the data and the variables (Dennis and Ventura, 2012; Gens and Domingos, 2013; Peharz et al., 2013; Rooshenas and Lowd, 2014; Adel et al., 2015; Vergari et al., 2015).”
Language modeling with sum-product networks (2014, background): “(Gens & Domingos [13]) An SPN can compute each”
On the Expressive Efficiency of Sum Product Networks (2014, methodology): “Among other uses [Gens and Domingos, 2013], this allows us to efficiently compute the partition function3 which normalizesΦ’s associated density functionpΦ by taking I = [n] andSi = Ri for eachi ∈ [n].”