ProbLP: A framework for low-precision probabilistic inference
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.
Code (1)
Similar Papers 제목 키워드 기반
Alexandria: Unsupervised High-Precision Knowledge Base Construction using a Probabilistic Program
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 PredictionDimensionality Reduction as Probabilistic Inference
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 ProgrammingWhen Do Credal Sets Stabilize? Fixed-Point Theorems for Credal Set Updates
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 LearningApproximate Bayesian Inference via Bitstring Representations
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 InferenceEquivariant Neural Belief Propagation
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 …