Density Functions of Statistical Probabilistic Programs
We present a transformer that takes a first order probabilistic program and returns a density function corresponding to this program. Alongside this we also present a type system that identifies the distributions these programs represent as absolutely continuous. These absolutely continuous distributions are precisely those that admit density functions. This work includes analysis on programs with both scoring con- structs and unbounded loops.
Tue 21 Jan Times are displayed in time zone: Saskatchewan, Central America change
15:35 - 17:45
|Coinductive Trees for Exact Inference of Probabilistic Programs|
|Name generation and Higher-order Probabilistic Programming (Or is new=rnd?)|
|Density Functions of Statistical Probabilistic Programs|
|Probabilistic Programming around Gaussian Processes|