# ProbLP: A framework for low-precision probabilistic inference

arXiv: https://arxiv.org/abs/2103.00216 · HTML: https://mlsanity.com/paper/2103.00216/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 24 references that are in the map.
- First posted on arXiv 27 Feb 2021.

## Builds on (most cited first, 3 of 3)

- [Neural Probabilistic Logic Programming in DeepProbLog](https://mlsanity.com/paper/1907.08194/) (2019)
- [UniMiB SHAR: a new dataset for human activity recognition using acceleration data from smartphones](https://mlsanity.com/paper/1611.07688/) (2016)
- [Learning Logistic Circuits](https://mlsanity.com/paper/1902.10798/) (2019)

## Built on by (most cited first, 2 of 2)

- [On Hardware-efficient Inference in Probabilistic Circuits](https://mlsanity.com/paper/2405.13639/) (2024)
- [Hardware-efficient tractable probabilistic inference for TinyML Neurosymbolic AI applications](https://mlsanity.com/paper/2507.05141/) (2025)

## Abstract (arXiv)

Bayesian reasoning is a powerful mechanism for probabilistic inference in smart edge-devices. During such inferences, a low-precision arithmetic representation can enable improved energy efficiency. However, its impact on inference accuracy is not yet understood. Furthermore, general-purpose hardware does not natively support low-precision representation. To address this, we propose ProbLP, a framework that automates the analysis and design of low-precision probabilistic inference hardware. It automatically chooses an appropriate energy-efficient representation based on worst-case error-bounds and hardware energy-models. It generates custom hardware for the resulting inference network exploiting parallelism, pipelining and low-precision operation. The framework is validated on several embedded-sensing benchmarks.