当前位置: X-MOL 学术Port. Math. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Notes on computational-to-statistical gaps: predictions using statistical physics
Portugaliae Mathematica ( IF 0.5 ) Pub Date : 2018-12-12 , DOI: 10.4171/pm/2014
Afonso Bandeira 1 , Amelia Perry 2 , Alexander Wein 1
Affiliation  

In these notes we describe heuristics to predict computational-to-statistical gaps in certain statistical problems. These are regimes in which the underlying statistical problem is information-theoretically possible although no efficient algorithm exists, rendering the problem essentially unsolvable for large instances. The methods we describe here are based on mature, albeit non-rigorous, tools from statistical physics. These notes are based on a lecture series given by the authors at the Courant Institute of Mathematical Sciences in New York City, on May 16th, 2017.

中文翻译:

关于计算与统计差距的说明:使用统计物理学进行预测

在这些笔记中,我们描述了启发式方法来预测某些统计问题中的计算与统计的差距。在这些机制中,尽管没有有效的算法存在,但潜在的统计问题在理论上是可能的,这使得该问题对于大型实例基本上无法解决。我们在此描述的方法基于来自统计物理学的成熟但不严格的工具。这些笔记基于作者于 2017 年 5 月 16 日在纽约市 Courant 数学科学研究所进行的系列讲座。
更新日期:2018-12-12
down
wechat
bug