PulseAugur
中
实时 17:28:45

新方法通过神经网络推进摊销贝叶斯推理 · 跟踪 2 个来源

两篇新提交至 arXiv 的研究论文介绍了用于摊销贝叶斯推理的新颖方法。第一篇论文提出使用辅助监督来缓解贝叶斯推理神经网络优化中的表示差距,从而实现更快的收敛和更好的性能,尤其是在数据有限的情况下。第二篇论文提出了一种用于任意结构多层模型上摊销贝叶斯推理的通用方法,该方法从有向无环图表示自动推导出因子分解和神经网络架构。这种方法保留了所有条件独立性假设,并与黄金标准采样器非常匹配,同时将推理简化为快速前向传播。 AI

影响 摊销贝叶斯推理的这些进展可以为复杂的 AI 系统中更有效和准确的统计建模提供支持。

排序理由 两篇发表在 arXiv 上的研究论文介绍了贝叶斯推理的新方法。

在 Hugging Face Daily Papers 阅读 →

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

新方法通过神经网络推进摊销贝叶斯推理 · 跟踪 2 个来源

本文如何被排名

Signal score
1 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
两篇发表在 arXiv 上的研究论文介绍了贝叶斯推理的新方法。
Source corroboration
3 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
2 days old
Coverage has settled into its steady-state source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

完整方法见我们的编辑标准。

报道来源 [3]

  1. Hugging Face Daily Papers TIER_1 English(EN) ·

    Amortized Bayesian Inference on Multilevel Models of Arbitrary Structure

    We develop a general method for amortized Bayesian inference on multilevel models of arbitrary structure. Given a generative model specified as a directed acyclic graph, our method automatically derives valid factorizations of the joint posterior and matching neural network archi…

  2. arXiv stat.ML TIER_1 English(EN) · Hans Olischl\"ager, Svenja Jedhoff, \v{S}imon Kucharsk\'y, Aayush Mishra, Stefan T. Radev, Paul B\"urkner ·

    利用辅助监督缓解摊销贝叶斯推理中的表示差距

    arXiv:2609.39525v1 Announce Type: new Abstract: Casting Bayesian inference as a neural network optimization problem targeting an amortized posterior is attractive, as it extends to otherwise intractable statistical models and offers near instantaneous inference for new datasets a…

  3. arXiv stat.ML TIER_1 English(EN) · Daniel Habermann, Andreas Bulling, Stefan T. Radev, Paul-Christian B\"urkner ·

    Amortized Bayesian Inference on Multilevel Models of Arbitrary Structure

    arXiv:2609.40024v1 Announce Type: new Abstract: We develop a general method for amortized Bayesian inference on multilevel models of arbitrary structure. Given a generative model specified as a directed acyclic graph, our method automatically derives valid factorizations of the j…