Tamara Broderick

Latest

• Finite mixture models do not reliably learn the number of components
• Power posteriors do not reliably learn the number of components in a finite mixture
• Finite mixture models are typically inconsistent for the number of components
• Exchangeable trait allocations
• Finite mixture models are typically inconsistent for the number of components
• Edge-exchangeable graphs and sparsity
• Paintboxes and probability functions for edge-exchangeable graphs
• Completely random measures for modeling power laws in graphs
• Edge-exchangeable graphs and sparsity
• Edge-exchangeable graphs, sparsity, and power laws