12 citations · 34 across the 8 of their papers we have counts for
Showing cs.PLShow all
2 papers · 1 filter
cs.PL2026
DeGAS: Gradient-Based Optimization of Probabilistic Programs without Sampling
Francesca Randone, Romina Doz, Mirco Tribastone +1
We present DeGAS, a differentiable Gaussian approximate semantics for loopless probabilistic programs that enables sample-free, gradient-based optimization in models with both cont…
cs.PL2023★ 12 cited
Inference of Probabilistic Programs with Moment-Matching Gaussian Mixtures
Francesca Randone, Luca Bortolussi, Emilio Incerto +1
Computing the posterior distribution of a probabilistic program is a hard task for which no one-fit-for-all solution exists. We propose Gaussian Semantics, which approximates the e…