Neural tensor contractions and the expressive power of deep neural quantum states
This work addresses the problem of representing complex quantum states efficiently for researchers in quantum physics and machine learning, offering a novel theoretical framework that is not incremental.
The paper establishes a direct connection between tensor networks and deep neural networks by constructing neural layers that efficiently perform tensor contractions, showing that neural-network states have the same or higher expressive power than variational tensor networks for many-body quantum states, with examples like matrix product states being efficiently representable by neural networks.
We establish a direct connection between general tensor networks and deep feed-forward artificial neural networks. The core of our results is the construction of neural-network layers that efficiently perform tensor contractions, and that use commonly adopted non-linear activation functions. The resulting deep networks feature a number of edges that closely matches the contraction complexity of the tensor networks to be approximated. In the context of many-body quantum states, this result establishes that neural-network states have strictly the same or higher expressive power than practically usable variational tensor networks. As an example, we show that all matrix product states can be efficiently written as neural-network states with a number of edges polynomial in the bond dimension and depth logarithmic in the system size. The opposite instead does not hold true, and our results imply that there exist quantum states that are not efficiently expressible in terms of matrix product states or PEPS, but that are instead efficiently expressible with neural network states.