Distinguishing close quantum states captures many problems in quantum algorithms and learning. It is known that distinguishing $\epsilon$-close states requires $O(\epsilon^{-2})$ copies, but given a state preparation oracle and its inverse, only $O(\epsilon^{-1})$ queries are required. However, \emph{inverse} can be hard to access in real world experiments. We study: what if you are given only the forward oracle? For a continuous time version of this problem, we show that $O(\epsilon^{-1})$ evolution time suffices, though the discrete query case remains open.

*We strongly encourage attendees to use their full name (and if possible, their UMD credentials) to join the zoom session.*