GradInf: Gradient Estimation as Probabilistic Inference

• URL: http://arxiv.org/abs/2607.07840v1
• Date: Wed, 08 Jul 2026 18:18:41 GMT
• Title: GradInf: Gradient Estimation as Probabilistic Inference
• Abstract summary: We develop a new approach to developing sound and efficient gradient estimators for probabilistic programs.<n>GradInf is a probabilistic programming system that facilitates the sound and automated implementation of gradient inference.
• Score: 41.324573619943955
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Gradient estimation -- the task of computing the gradient of the expected value of a probabilistic program -- has diverse applications in scientific computing, but is notoriously difficult because of issues such as high-dimensional integration, discrete random choices, and complex stochastic dependencies. This article introduces gradient inference, a new approach to developing sound and efficient gradient estimators for probabilistic programs. Gradient inference rests on a formal reduction from a gradient estimation problem to a closely related probabilistic inference problem, whose solution can be differentiated to obtain a gradient estimator. This inference problem is obtained by applying two powerful statistical operations -- coupling and factorization -- to the input probabilistic program. Our reduction lets us leverage the rich toolkit of probabilistic inference algorithms to design novel gradient estimators that extend and improve upon existing methods. We introduce GradInf, a probabilistic programming system that facilitates the sound and automated implementation of gradient inference. GradInf is centered around programmable source-to-source transformations for coupling and factorizing higher-order probabilistic programs, whose soundness is proven in terms of a denotational semantics. Key to our development is the use of information-flow typing to allow random choices in a probabilistic program to be factored out and partially evaluated, which improves our ability to deploy sophisticated probabilistic inference algorithms. The resulting system offers practitioners a principled framework for designing gradient estimators. We apply GradInf to several challenging case studies, showing that it can express prominent gradient estimators from the literature and enables the construction of new state-of-the-art estimators that outperform the best existing baselines.

Related papers

• Efficient Model-Free Exploration in Low-Rank MDPs [76.87340323826945]
  Low-Rank Markov Decision Processes offer a simple, yet expressive framework for RL with function approximation. Existing algorithms are either (1) computationally intractable, or (2) reliant upon restrictive statistical assumptions. We propose the first provably sample-efficient algorithm for exploration in Low-Rank MDPs.
  arXiv  Detail & Related papers  (2023-07-08T15:41:48Z)
• Fast and Correct Gradient-Based Optimisation for Probabilistic Programming via Smoothing [0.0]
  We study the foundations of variational inference, which frames posterior inference as an optimisation problem. We endow our language with both a measurable and a smoothed (approximate) value semantics. We show that our approach has a similar convergence as a key competitor, but is simpler, faster, and attains orders of magnitude reduction in work-normalised variance.
  arXiv  Detail & Related papers  (2023-01-09T15:12:45Z)
• Reliability analysis of discrete-state performance functions via adaptive sequential sampling with detection of failure surfaces [0.0]
  The paper presents a new efficient and robust method for rare event probability estimation. The method can estimate the probabilities of multiple failure types. It can accommodate this information to increase the accuracy of the estimated probabilities.
  arXiv  Detail & Related papers  (2022-08-04T05:59:25Z)
• Probabilistic Gradient Boosting Machines for Large-Scale Probabilistic Regression [51.770998056563094]
  Probabilistic Gradient Boosting Machines (PGBM) is a method to create probabilistic predictions with a single ensemble of decision trees. We empirically demonstrate the advantages of PGBM compared to existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-06-03T08:32:13Z)
• Statistical Inference for Polyak-Ruppert Averaged Zeroth-order Stochastic Gradient Algorithm [10.936043362876651]
  In the last decade, estimating or training in several machine learning models has become synonymous with running gradient algorithms. We first establish a central limit for Polyak-Ruppert averaged gradient algorithm in the zeroth-order setting.
  arXiv  Detail & Related papers  (2021-02-10T00:47:20Z)
• Zeroth-Order Hybrid Gradient Descent: Towards A Principled Black-Box Optimization Framework [100.36569795440889]
  This work is on the iteration of zero-th-order (ZO) optimization which does not require first-order information. We show that with a graceful design in coordinate importance sampling, the proposed ZO optimization method is efficient both in terms of complexity as well as as function query cost.
  arXiv  Detail & Related papers  (2020-12-21T17:29:58Z)
• Evaluating probabilistic classifiers: Reliability diagrams and score decompositions revisited [68.8204255655161]
  We introduce the CORP approach, which generates provably statistically Consistent, Optimally binned, and Reproducible reliability diagrams in an automated way. Corpor is based on non-parametric isotonic regression and implemented via the Pool-adjacent-violators (PAV) algorithm.
  arXiv  Detail & Related papers  (2020-08-07T08:22:26Z)
• Instability, Computational Efficiency and Statistical Accuracy [101.32305022521024]
  We develop a framework that yields statistical accuracy based on interplay between the deterministic convergence rate of the algorithm at the population level, and its degree of (instability) when applied to an empirical object based on $n$ samples. We provide applications of our general results to several concrete classes of models, including Gaussian mixture estimation, non-linear regression models, and informative non-response models.
  arXiv  Detail & Related papers  (2020-05-22T22:30:52Z)
• Scalable Approximate Inference and Some Applications [2.6541211006790983]
  In this thesis, we propose a new framework for approximate inference. Our proposed four algorithms are motivated by the recent computational progress of Stein's method. Results on simulated and real datasets indicate the statistical efficiency and wide applicability of our algorithm.
  arXiv  Detail & Related papers  (2020-03-07T04:33:27Z)
• Stochastically Differentiable Probabilistic Programs [18.971852464650144]
  The existence of discrete random variables prohibits many basic gradient-based inference engines. We present a novel approach to run inference efficiently and robustly in such programs using Markov Chain Monte Carlo family of algorithms.
  arXiv  Detail & Related papers  (2020-03-02T08:04:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.