arXiv:2509.25126stat.MLcs.LG2025-09

研究正交分解张量的谱学习,揭示高效算法与统计极限的边界。

On Spectral Learning for Odeco Tensors: Perturbation, Initialization, and Algorithms

  • 基于张量谱分解,突破矩阵依赖特征值间隔的限制。
  • 发现迭代算法在噪声下仍具统计效率,但初始化成主要瓶颈。
  • 给出扰动分析与优化几何,指导高效算法设计。

我们研究正交分解(odeco)张量的谱学习方法,强调统计极限、优化几何与初始化之间的相互作用。与矩阵不同,odeco张量的恢复不依赖于特征值间隔,因此在噪声下表现出更强的鲁棒性。尽管如张量幂迭代等迭代方法具有统计效率,但初始化成为主要计算瓶颈。本文分析了扰动界、非凸优化性质以及初始化策略,厘清了何时高效算法可达到统计极限,何时存在根本性障碍。

原文摘要 · Abstract (English)

We study spectral learning for orthogonally decomposable (odeco) tensors, emphasizing the interplay between statistical limits, optimization geometry, and initialization. Unlike matrices, recovery for odeco tensors does not hinge on eigengaps, yielding improved robustness under noise. While iterative methods such as tensor power iterations can be statistically efficient, initialization emerges as the main computational bottleneck. We investigate perturbation bounds, non-convex optimization analysis, and initialization strategies, clarifying when efficient algorithms attain statistical limits and when fundamental barriers remain.

张量分解谱学习非凸优化

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。