The field of machine learning on quantum computers got a boost from new research. The research removed a potential roadblock to the practical implementation of quantum neural networks. Theorists had previously thought an exponentially large training set would be required to train a quantum neural network. The quantum No-Free-Lunch theorem developed by Los Alamos National Laboratory shows that quantum entanglement eliminates this exponential overhead.
The research paper has been published in Physical Review Letters. The classical No-Free-Lunch theorem states that any machine-learning algorithm is as good as any other when their performance is averaged over all possible functions connecting the data to their labels. A direct consequence of this theorem that showcases the power of data in classical machine learning. The more data one has, the better the average performance. Data is the currency in machine learning that ultimately limits performance.
The new Los Alamos No-Free-Lunch theorem showed that in the quantum regime entanglement is also a currency. One can be exchanged for data to reduce data requirements.
Scientists used a Rigetti quantum computer. They entangled the quantum data set with a reference system to verify the new theorem.
Scientists demonstrated on quantum hardware. They can effectively violate the standard No-Free-Lunch theorem using entanglement. The new formula of the theorem held up under experimental test. The theorem suggests that entanglement should be considered a valuable resource in quantum machine learning with big data. Classical neural networks depend only on big data.
