On the role of weight sharing during deep option learning
Matthew Riemer, Ignacio Cases, et al.
AAAI 2020
The boundary operator is a linear operator that acts on a collection of high-dimensional binary points (simplices) and maps them to their boundaries. This boundary map is one of the key components in numerous applications, including differential equations, machine learning, computational geometry, machine vision, and control systems. We consider the problem of representing the full boundary operator on a quantum computer. We first prove that the boundary operator has a special structure in the form of a complete sum of fermionic creation and annihilation operators. We then use the fact that these operators pairwise anticommute to produce an O(n)-depth circuit that exactly implements the boundary operator without any Trotterization or Taylor-series approximation errors. Having fewer errors reduces the number of shots required to obtain desired accuracies.
Matthew Riemer, Ignacio Cases, et al.
AAAI 2020
Parikshit Ram, Tim Klinger, et al.
IJCAI 2024
Zijun Cui, Hanjing Wang, et al.
UAI 2022
Fabiana Fournier, Lior Limonad, et al.
BPM 2024