Abstract
The problem of optimizing over random structures emerges in many areas of science and engineering, ranging from statistical physics to machine learning and artificial intelligence. For many such structures, finding optimal solutions by means of fast algorithms is not known and often is believed not to be possible. At the same time, the formal hardness of these problems in the form of the complexity-theoretic NP-hardness is lacking. A new approach for algorithmic intractability in random structures is described in this article, which is based on the topological disconnectivity property of the set of pairwise distances of near-optimal solutions, called the Overlap Gap Property. The article demonstrates how this property 1) emerges in most models known to exhibit an apparent algorithmic hardness; 2) is consistent with the hardness/tractability phase transition for many models analyzed to the day; and, importantly, 3) allows to mathematically rigorously rule out a large class of algorithms as potential contenders, specifically the algorithms that exhibit the input stability (insensitivity).
Publisher
Proceedings of the National Academy of Sciences
Reference69 articles.
1. R. Vershynin , High-Dimensional Probability: An Introduction with Applications in Data Science (Cambridge Series in Statistical and Probabilistic Mathematics, Cambridge University Press, Cambridge, UK, 2018), vol. 47.
2. P. Bühlmann , S. Van De Geer , Statistics for High-Dimensional Data: Methods, Theory and Applications (Springer Series in Statistics, Springer Science & Business Media, Berlin, Germany, 2011).
3. S. Foucart , H. Rauhut , A Mathematical Introduction to Compressive Sensing (Applied and Numerical Harmonic Analysis, Birkhäuser, New York, 2013).
4. E. Farhi , D. Gamarnik , S. Gutmann , The quantum approximate optimization algorithm needs to see the whole graph: A typical case. arXiv [Preprint] (2020). https://arxiv.org/abs/2004.09002 (Accessed 15 September 2021).
5. E. Farhi , D. Gamarnik , S. Gutmann , The quantum approximate optimization algorithm needs to see the whole graph: Worst case examples. arXiv [Preprint] (2020). https://arxiv.org/abs/2005.08747 (Accessed 15 September 2021).
Cited by
25 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献