no code implementations • 3 May 2022 • V. Akshay, H. Philathong, E. Campos, D. Rabinovich, I. Zacharov, Xiao-Ming Zhang, J. Biamonte
Focusing on random instances of MAX-2-SAT, we test our predictive model against simulated data with up to 15 qubits.
no code implementations • 25 Jun 2021 • E. Campos, D. Rabinovich, V. Akshay, J. Biamonte
Doing so we discovered that such training always saturates -- called \textit{training saturation} -- at some depth $p^*$, meaning that past a certain depth, overlap can not be improved by adding subsequent layers.