Numerical circuit synthesis and compilation for multi-state preparation

Near-term quantum computers have significant error rates and short coherence times, so compilation of circuits to be as short as possible is essential. Two types of compilation problems are typically considered: circuits to prepare a given state from a fixed input state, called "state preparation"; and circuits to implement a given unitary operation, for example by "unitary synthesis". In this paper we solve a more general problem: the transformation of a set of $m$ states to another set of $m$ states, which we call "multi-state preparation". State preparation and unitary synthesis are special cases; for state preparation, $m=1$, while for unitary synthesis, $m$ is the dimension of the full Hilbert space. We generate and optimize circuits for multi-state preparation numerically. In cases where a top-down approach based on matrix decompositions is also possible, our method finds circuits with substantially (up to 40%) fewer two-qubit gates. We discuss possible applications, including efficient preparation of macroscopic superposition ("cat") states and synthesis of quantum channels.