Probabilistic Programming with Programmable Variational Inference
Compared to the wide array of advanced Monte Carlo methods supported by modern probabilistic programming languages (PPLs), PPL support for variational inference (VI) is less developed: users are typically limited to a predefined selection of variational objectives and gradient estimators, which are implemented monolithically (and without formal correctness arguments) in PPL backends. In this paper, we propose a more modular approach to supporting variational inference in PPLs, based on compositional program transformation. In our approach, variational objectives are expressed as programs, that may employ first-class constructs for computing densities of and expected values under user-defined models and variational families. We then transform these programs systematically into unbiased gradient estimators for optimizing the objectives they define. Our design enables modular reasoning about many interacting concerns, including automatic differentiation, density accumulation, tracing, and the application of unbiased gradient estimation strategies. Additionally, relative to existing support for VI in PPLs, our design increases expressiveness along three axes: (1) it supports an open-ended set of user-defined variational objectives, rather than a fixed menu of options; (2) it supports a combinatorial space of gradient estimation strategies, many not automated by today's PPLs; and (3) it supports a broader class of models and variational families, because it supports constructs for approximate marginalization and normalization (previously introduced only for Monte Carlo inference). We implement our approach in an extension to the Gen probabilistic programming system (genjax.vi, implemented in JAX), and evaluate on several deep generative modeling tasks, showing minimal performance overhead vs. hand-coded implementations and performance competitive with well-established open-source PPLs.
Code (0)
등록된 구현이 없습니다.
Tasks
Probabilistic ProgrammingVariational InferenceMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Venture: a higher-order probabilistic programming platform with programmable inference
We describe Venture, an interactive virtual machine for probabilistic programming that aims to be sufficiently expressive, extensible, and efficient for general-purpose use. Like Church, probabilistic models and inferenc…
Probabilistic ProgrammingVariational InferenceLearning Proposals for Probabilistic Programs with Inference Combinators
We develop operators for construction of proposals in probabilistic programs, which we refer to as inference combinators. Inference combinators define a grammar over importance samplers that compose primitive operations …
Deep Probabilistic Programming
We propose Edward, a Turing-complete probabilistic programming language. Edward defines two compositional representations---random variables and inference. By treating inference as a first class citizen, on a par with mo…
Probabilistic ProgrammingVariational InferenceDiffusion models for probabilistic programming
We propose Diffusion Model Variational Inference (DMVI), a novel method for automated approximate inference in probabilistic programming languages (PPLs). DMVI utilizes diffusion models as variational approximations to t…
Probabilistic ProgrammingVariational InferenceModular Deep Probabilistic Programming
Modularity is a key feature of deep learning libraries but has not been fully exploited for probabilistic programming. We propose to improve modularity of probabilistic programming language by offering not only plain pro…
Probabilistic ProgrammingVariational Inference