Finite mixture models do not reliably learn the number of components
Diana Cai * 1 Trevor Campbell * 2 Tamara Broderick 3
Abstract hakaran et al., 2016), microscopy groups (Rubin-Delanchy
Scientists and engineers are often interested in et al., 2015; Griffie et al., 2016), haplotypes (Xing et al.,
learning the number of subpopulations (or com- 2006), switching Markov regimes in US dollar exchange
ponents) present in a data ...


雷达卡




京公网安备 11010802022788号







