新论文探讨深度神经网络更快的量化不确定性方法

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-14 10:18

研究人员在arXiv上发表了一篇关于深度神经网络的基于评分的鞅后验（SMPs）的论文。该方法为机器学习中量化不确定性的传统马尔可夫链蒙特卡洛技术提供了一种潜在的更快替代方案。论文探讨了SMPs在深度神经网络中推断参数的应用，并将其功效与现有的蒙特卡洛方法进行了比较。 AI

影响这项研究可能带来更有效的深度学习模型不确定性量化。

排序理由该集群包含一篇在arXiv上发表的学术论文，详细介绍了一种用于深度神经网络的新统计方法。

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]

arXiv stat.ML TIER_1 English(EN) · Abylay Zhumekenov, Ajay Jasra, Mohamed Maama, Raul Tempone · 2026-06-16 04:00

Score-Based Martingale Posteriors for Deep Neural Networks

arXiv:2606.15725v1 Announce Type: cross Abstract: In this paper we investigate the efficacy of the score-based martingale posteriors (SMP) (Cui & Walker, 2025; Fong et al., 2023) in the context of modern and large-scale machine learning problems and its potential for meaningful u…
arXiv stat.ML TIER_1 English(EN) · Raul Tempone · 2026-06-14 10:18

Score-Based Martingale Posteriors for Deep Neural Networks

In this paper we investigate the efficacy of the score-based martingale posteriors (SMP) (Cui & Walker, 2025; Fong et al., 2023) in the context of modern and large-scale machine learning problems and its potential for meaningful uncertainty quantification. SMPs work with a stocha…