PulseAugur
中
实时 11:18:39
English(EN) Exponential-Family Tensor Completion via Nonconvex Dual Total-Variation Regularization

新的对偶全变分（DTV）正则化张量补全方法详解

作者 PulseAugur 编辑部 · [2 个来源] ·

研究人员开发了一种使用对偶全变分（DTV）正则化的新张量补全理论框架。该方法旨在处理指数族噪声，其中包含高斯和泊松等常见分布。提出的DTV正则化器能够捕捉梯度张量中的稀疏性和低秩结构，并且该研究建立了接近 minimax 下界的恢复误差的理论上限。在合成数据、图像和视频数据上的实验证明了该方法的有效性。 AI

排序理由 该聚类包含一篇详细介绍新统计学方法的学术论文。[lever_c_demoted from research: ic=2 ai=0.4]

在 arXiv stat.ML 阅读 →

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

新的对偶全变分（DTV）正则化张量补全方法详解

报道来源 [2]

  1. arXiv stat.ML TIER_1 English(EN) · Wenfei Cao, Yang Chen, Qibin Zhao, Jinglai Li, Andrzej Cichocki ·

    Exponential-Family Tensor Completion via Nonconvex Dual Total-Variation Regularization

    arXiv:2606.30958v1 Announce Type: cross Abstract: With the emergence of various tensor data, tensor completion from partial measurements has attracted widespread attention in data science and signal processing. Total Variation (TV) has been widely used as an effective regularizat…

  2. arXiv stat.ML TIER_1 English(EN) · Andrzej Cichocki ·

    Exponential-Family Tensor Completion via Nonconvex Dual Total-Variation Regularization

    With the emergence of various tensor data, tensor completion from partial measurements has attracted widespread attention in data science and signal processing. Total Variation (TV) has been widely used as an effective regularization technique for tensor completion; however, theo…

相关实体

相关话题