Probabilistic Generating Circuits

Abstract

Generating functions, which are widely used in combinatorics and probability theory, encode function values into the coefficients of a polynomial. In this paper, we explore their use as a tractable probabilistic model, and propose probabilistic generating circuits (PGCs) for their efficient representation. PGCs are strictly more expressive efficient than many existing tractable probabilistic models, including determinantal point processes (DPPs), probabilistic circuits (PCs) such as sum-product networks, and tractable graphical models. We contend that PGCs are not just a theoretical framework that unifies vastly different existing models, but also show great potential in modeling realistic data. We exhibit a simple class of PGCs that are not trivially subsumed by simple combinations of PCs and DPPs, and obtain competitive performance on a suite of density estimation benchmarks. We also highlight PGCs' connection to the theory of strongly Rayleigh distributions.

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Solving the apparent diversity-accuracy dilemma of recommender systems
• Sum-Product Networks: A New Deep Architecture
• Eynard-Mehta theorem, Schur process, and their pfaffian analogs
• Learning the Parameters of Determinantal Point Process Kernels
• On the Expressive Efficiency of Sum Product Networks
• Expectation-Maximization for Learning Determinantal Point Processes
• Fixed-point algorithms for learning determinantal point processes
• Learning Nonsymmetric Determinantal Point Processes
• Kronecker Determinantal Point Processes
• Fast Mixing Markov Chains for Strongly Rayleigh Measures, DPPs, and Constrained Sampling
• Flexible Modeling of Diversity with Strongly Log-Concave Distributions

Cited by in corpus (1)

• Sum-Product-Attention Networks: Leveraging Self-Attention in Probabilistic Circuits