no code implementations • pproximateinference AABI Symposium 2019 • Chunlin Ji, Bin Liu, Yingkai Jiang, Ke Deng
We propose an evidence upper bound (EUBO) to act as the surrogate loss, and fit a DP mixture to the given data by minimizing the EUBO, which is equivalent to minimizing the KL-divergence between the target distribution and the DP mixture.