6 papers
Statistical Limits of Supervised Quantum Learning
Carlo Ciliberto, Andrea Rocchetto, Alessandro Rudi +1
Within the framework of statistical learning theory it is possible to bound the minimum number of samples required by a learner to reach a target accuracy. We show that if the boun…
Decomposition of Pauli groups via weak central products
Andrea Rocchetto, Francesco G. Russo
For any and odd prime power , for , and for any , we show a result of decomposition for Pauli groups $\mathcal{P}_{n,\math…
Modelling Non-Markovian Quantum Processes with Recurrent Neural Networks
Leonardo Banchi, Edward Grant, Andrea Rocchetto +1
Quantum systems interacting with an unknown environment are notoriously difficult to model, especially in presence of non-Markovian and non-perturbative effects. Here we introduce…
Approximating Hamiltonian dynamics with the Nyström method
Alessandro Rudi, Leonard Wossnig, Carlo Ciliberto +3
Simulating the time-evolution of quantum mechanical systems is BQP-hard and expected to be one of the foremost applications of quantum computers. We consider classical algorithms f…
Learning DNFs under product distributions via μ-biased quantum Fourier sampling
Varun Kanade, Andrea Rocchetto, Simone Severini
We show that DNF formulae can be quantum PAC-learned in polynomial time under product distributions using a quantum example oracle. The best classical algorithm (without access to…
Experimental learning of quantum states
Andrea Rocchetto, Scott Aaronson, Simone Severini +5
The number of parameters describing a quantum state is well known to grow exponentially with the number of particles. This scaling clearly limits our ability to do tomography to sy…