离散扩散的类别马尔可夫随机场样本复杂度界

1. 12:00
   arXiv · Statistics Machine Learning

   离散扩散下分类马尔可夫随机场的样本复杂度界

   summary_zh: 该研究针对分类马尔可夫随机场提出离散扩散采样方法，给出端到端样本复杂度界，复杂度显式依赖词表大小、MRF 交互阶数和样本量。作者提出 pinning decomposition 将离散 score 分解为时间与目标可分离的乘积形式，并设计 weight-sharing neural score learner 结合 τ-leaping 进行采样。

Current heat 8·Comparable peak 10（Oct 2）·Comparable change over 24 hours –

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.