PulseAugur
实时 20:28:33
None Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep Learning

贝叶斯深度学习通过新的采样和推理方法取得进展

两篇新研究论文提出了贝叶斯深度学习的进展,重点是改进神经网络的推理方法。第一篇论文认为,基于采样的推理(SAI)在计算上已与优化方法相当,应成为不确定性量化的标准。第二篇论文介绍了一种新颖的、可扩展的基于分数的变分推理方法,该方法避免了重参数化采样,并且可以处理像Vision Transformers这样的大规模网络,解决了其他方法中存在的模式崩溃等问题。 AI

影响 这些论文推动了贝叶斯深度学习的核心研究,有望改进不确定性量化,并为复杂模型实现更具可扩展性的推理。

排序理由 两篇在arXiv上发表的学术论文,提出了贝叶斯深度学习的新方法。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.LG TIER_1 · Emanuel Sommer, David R\"ugamer ·

    Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep Learning

    arXiv:2605.21765v1 Announce Type: new Abstract: The practical adoption of sampling-based inference (SAI) in Bayesian neural networks (BNNs) remains limited, partly due to persistent misconceptions about the feasibility and efficiency of sampling. This position paper argues that S…

  2. arXiv cs.LG TIER_1 · Minyoung Kim ·

    Large-scale Score-based Variational Posterior Inference for Bayesian Deep Neural Networks

    arXiv:2602.05873v2 Announce Type: replace Abstract: Bayesian (deep) neural networks (BNN) are often more attractive than the vanilla point-estimate deep learning in various aspects including uncertainty quantification, robustness to noise, resistance to overfitting, and more. The…