arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.08895stat.MLcs.LG
收藏

结构预测中精确推理的基本界限

On the Fundamental Limits of Exact Inference in Structured Prediction

Purdue University(普渡大学)

Hanbyul Lee, Kevin Bello, Jean Honorio

摘要:

推理是结构化预测中的一项主要任务,它可以很自然地用图来建模。在马尔可夫随机场的背景下,噪声观测对应的节点和边缘通常涉及,和精确推理的目标是恢复未知的真实标签为每个节点精确。本文的重点是不考虑计算效率的精确恢复的基本限制,假设由Globerson等人提出的生成过程。(2015)。我们得到了任何算法的必要条件和极大似然估计以高概率实现精确恢复的充分条件,并揭示了充分和必要条件是紧到一个对数因子的广泛的图形。最后,我们证明了Bello和Honorio(2019)的计算易处理方法的基本极限和性能之间存在差距,这意味着需要进一步开发精确推理的算法。

英文摘要:

Inference is a main task in structured prediction and it is naturally modeled with a graph. In the context of Markov random fields, noisy observations corresponding to nodes and edges are usually involved, and the goal of exact inference is to recover the unknown true label for each node precisely. The focus of this paper is on the fundamental limits of exact recovery irrespective of computational efficiency, assuming the generative process proposed by Globerson et al. (2015). We derive the necessary condition for any algorithm and the sufficient condition for maximum likelihood estimation to achieve exact recovery with high probability, and reveal that the sufficient and necessary conditions are tight up to a logarithmic factor for a wide range of graphs. Finally, we show that there exists a gap between the fundamental limits and the performance of the computationally tractable method of Bello and Honorio (2019), which implies the need for further development of algorithms for exact inference.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑