paper-with-me

홈 › Papers

ProbLP: A framework for low-precision probabilistic inference

2021-02-27 · Nimish Shah, Laura I. Galindez Olascoaga, Wannes Meert, Marian Verhelst

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.

📄 PDF Abstract BibTeX arXiv:2103.00216

Code (1)

nimish15shah/ProbLP 공식 구현

Similar Papers 제목 키워드 기반

Alexandria: Unsupervised High-Precision Knowledge Base Construction using a Probabilistic Program

2018-11-17 · AKBC 2019 · John Winn, John Guiver, Sam Webster, Yordan Zaykov 외

Creating a knowledge base that is accurate, up-to-date and complete remains a significant challenge despite substantial efforts in automated knowledge base construction. In this paper, we present Alexandria -- a system …

Knowledge Base ConstructionVocal Bursts Intensity Prediction

Dimensionality Reduction as Probabilistic Inference

2023-04-15 · Aditya Ravuri, Francisco Vargas, Vidhi Lalchand, Neil D. Lawrence

Dimensionality reduction (DR) algorithms compress high-dimensional data into a lower dimensional representation while preserving important features of the data. DR is a critical step in many analysis pipelines as it enab…

Dimensionality ReductionGaussian ProcessesProbabilistic Programming

When Do Credal Sets Stabilize? Fixed-Point Theorems for Credal Set Updates

2025-10-06 · Michele Caprio, Siu Lun Chau, Krikamol Muandet arxiv

Many machine learning algorithms rely on iterative updates of uncertainty representations, ranging from variational inference and expectation-maximization, to reinforcement learning, continual learning, and multi-agent l…

Reinforcement LearningContinual Learning

Approximate Bayesian Inference via Bitstring Representations

2025-08-19 · Aleksanteri Sladek, Martin Trapp, Arno Solin arxiv

The machine learning community has recently put effort into quantized or low-precision arithmetics to scale large models. This paper proposes performing probabilistic inference in the quantized, discrete parameter space …

Interpretable Machine LearningBayesian Inference

Equivariant Neural Belief Propagation

2026-06-04 · Zehua Cheng, Wei Dai, Jiahao Sun arxiv

Probabilistic inference over spatially embedded variables requires beliefs that respect $SE(3)$ symmetry, yet existing equivariant networks produce only scalars and vectors -- not the rank-2 precision tensors needed for …