English(EN) Truncated Neural Likelihood Estimation for Simulation-Based Inference in State-Space Models

新的T-SNL算法增强了状态空间模型的推断能力

作者 PulseAugur 编辑部 · [3 个来源] · 2026-05-20 23:01

研究人员开发了一种名为截断神经似然（T-SNL）的新算法，以改进状态空间模型（SSM）中的参数推断。现有的顺序神经似然（SNL）等方法在长序列的样本效率和可扩展性方面存在困难。T-SNL解决了这些限制，提供了一种更准确、更稳定、更具摊销性的方法，在样本效率和鲁棒性方面优于以前的方法。 AI

影响为复杂时间序列模型中的参数推断引入了一种更有效、更具可扩展性的方法。

排序理由该集群包含一篇详细介绍统计推断新算法的学术论文。

AI 生成摘要 · Google Gemini · 来自 3 个来源。我们如何撰写摘要 →

报道来源 [3]

arXiv stat.ML TIER_1 English(EN) · Shiyi Sun, Geoff K. Nicholls, Jeong Eun Lee · 2026-05-25 04:00

Amortized Simulation-Based Inference in Generalized Bayes via Neural Posterior Estimation

arXiv:2601.22367v2 Announce Type: replace Abstract: Generalized Bayesian Inference (GBI) tempers a loss with a temperature $\beta > 0$ to mitigate overconfidence and improve robustness under model misspecification, but existing GBI methods typically rely on costly MCMC or SDE-bas…
arXiv stat.ML TIER_1 English(EN) · Kostas Tsampourakis, V\'ictor Elvira · 2026-05-22 04:00

Truncated Neural Likelihood Estimation for Simulation-Based Inference in State-Space Models

arXiv:2605.21805v1 Announce Type: cross Abstract: State-space models (SSMs) are powerful probabilistic tools for modeling time-varying systems with latent dynamics. Inference in SSMs involves the estimation of latent states and parameters. In this work, we focus on parameter infe…
arXiv stat.ML TIER_1 English(EN) · Víctor Elvira · 2026-05-20 23:01

Truncated Neural Likelihood Estimation for Simulation-Based Inference in State-Space Models

State-space models (SSMs) are powerful probabilistic tools for modeling time-varying systems with latent dynamics. Inference in SSMs involves the estimation of latent states and parameters. In this work, we focus on parameter inference, which for SSMs is in general a very challen…