POPL 2026
Sun 11 - Sat 17 January 2026 Rennes, France
Fri 16 Jan 2026 14:50 - 15:15 at Nef - Probabilistic Programming Chair(s): Michele Pagani

We present GenJAX, a new language and compiler for vectorized
programmable probabilistic inference.
GenJAX integrates the vectorizing map (vmap) operation from
array programming frameworks such as JAX
into the programmable inference paradigm, enabling compositional
vectorization of features such as probabilistic program traces,
stochastic branching
(for expressing mixture models), and programmable inference interfaces
for writing custom probabilistic inference algorithms.
We formalize vectorization as a source-to-source program
transformation on a core calculus for probabilistic programming ($\gen$), and
prove that it correctly vectorizes both modeling and inference operations.
We have implemented our approach in
\href{https://github.com/probcomp/genjax}{the GenJAX language and
compiler}, and have empirically evaluated this implementation on
several benchmarks and case studies. Our results show that our implementation
supports a wide and expressive set of programmable inference
patterns and delivers
performance comparable to hand-optimized JAX code.

Fri 16 Jan

Displayed time zone: Brussels, Copenhagen, Madrid, Paris change

14:00 - 15:40
Probabilistic ProgrammingPOPL at Nef
Chair(s): Michele Pagani ENS Lyon
14:00
25m
Talk
Optimising Density Computations in Probabilistic Programs via Automatic Loop Vectorisation
POPL
Sangho Lim KAIST, Hyoungjin Lim KAIST, Wonyeol Lee POSTECH, Xavier Rival Inria - CNRS - Ecole Normale Superieure de Paris - PSL University, Hongseok Yang KAIST
DOI
14:25
25m
Talk
Probabilistic Concurrent Reasoning in Outcome Logic: Independence, Conditioning, and InvariantsDistinguished Paper
POPL
Noam Zilberstein Cornell University, Alexandra Silva Cornell University, Joseph Tassarotti New York University
DOI
14:50
25m
Talk
Probabilistic Programming with Vectorized Programmable InferenceRemote
POPL
McCoy Reynolds Becker MIT, Mathieu Huot MIT, George Matheos Massachusetts Institute of Technology, Xiaoyan Wang Massachusetts Institute of Technology, Karen Chung Massachusetts Institute of Technology, Colin Smith Massachusetts Institute of Technology, Sam Ritchie Massachusetts Institute of Technology, Rif A. Saurous Google, Alexander K. Lew Yale University, Martin C. Rinard Massachusetts Institute of Technology, Vikash K. Mansinghka Massachusetts Institute of Technology
DOI
15:15
25m
Talk
Tropical Mathematics and the Lambda-Calculus II: Tropical Geometry of Probabilistic Programming Languages
POPL
Davide Barbarossa University of Bath, Paolo Pistone Université Claude Bernard Lyon 1
DOI