用处理器原生方法实现确定性状态估计，速度提升805倍且精度不降。
Dynamic Online Processor-Native Inference for State Estimation
- 通过原生操作实现不确定度传播与推理，保证延迟确定、内存可控。
- 在三个非线性系统上对比，模型评估速度比蒙特卡洛快805倍，结果一致。
- 适合对实时性要求高、需稳定延迟的传感器融合与状态估计场景。
依赖传感器的驱动型应用越来越多地采用贝叶斯方法，从噪声测量和物理模型中推断动态系统的潜在状态。然而，似然计算仍是获得精确后验分布和高效推理的关键瓶颈。本文提出一种贝叶斯滤波技术，利用处理器原生不确定性追踪来同时实现不确定性传播与推理。该方法通过原生操作实现确定性分层重要性重构，为任意以程序代码形式编写的模型提供确定性延迟和有界内存使用。在三个非线性状态空间系统上的基准测试表明，该方法相比粒子滤波和基于蒙特卡洛的似然估计器，在模型评估时实现了高达805倍的平均加速，且结果质量相当；在后验推理中表现出帕累托占优的精度-延迟权衡，同时在均方根误差（RMSE）上与基线粒子滤波器保持竞争力。
原文摘要 · Abstract (English)
Sensor-rich data-driven applications increasingly use Bayesian approaches to infer latent states of dynamic systems from noisy sensor measurements and physical models. Yet the computation of the likelihood remains an essential bottleneck for accurate posteriors and performant inference. This paper presents a Bayesian filtering technique that uses processor-native uncertainty tracking for both uncertainty propagation and inference. The technique implements deterministic hierarchical importance restructuring through a native operation, giving deterministic latency and bounded memory use for arbitrary models written as program code. Benchmarks across three nonlinear state-space systems compare the approach against particle filters and Monte-Carlo-based likelihood estimators. The technique enables deterministic approximate filtering with as high as 805$\times$ average speedup against direct Monte Carlo work at matched result quality for model evaluation, and Pareto-dominant accuracy-latency trade-offs for posterior inference while remaining competitive in RMSE with baseline particle filters.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。