One T Gate Makes Distribution Learning Hard

arxiv(2023)

引用 1|浏览17
暂无评分
摘要
The task of learning a probability distribution from samples is ubiquitous across the natural sciences. The output distributions of local quantum circuits are of central importance in both quantum advantage proposals and a variety of quantum machine learning algorithms. In this work, we extensively characterize the learnability of output distributions of local quantum circuits. Firstly, we contrast learnability with simulatability by showing that Clifford circuit output distributions are efficiently learnable, while the injection of a single T gate renders the density modeling task hard for any depth d 1/4 n & omega;o1 thorn . We further show that the task of generative modeling universal quantum circuits at any depth d 1/4 n & omega;o1 thorn is hard for any learning algorithm, classical or quantum, and that for statistical query algorithms, even depth d 1/4 & omega;1/2logon thorn ? Clifford circuits are hard to learn. Our results show that one cannot use the output distributions of local quantum circuits to provide a separation between the power of quantum and classical generative modeling algorithms, and therefore provide evidence against quantum advantages for practically relevant probabilistic modeling tasks.
更多
查看译文
关键词
<mmlmath xmlnsmml=http//wwww3org/1998/math/mathml,distribution learning,gate
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要