Hyper-optimized compressed contraction of tensor networks with arbitrary geometry

Tensor network contraction is central to problems ranging from many-body physics to computer science. We describe how to approximate tensor network contraction through bond compression on arbitrary graphs. In particular, we introduce a hyper-optimization over the compression and contraction strategy itself to minimize error and cost. We demonstrate that our protocol outperforms both hand-crafted contraction strategies as well as recently proposed general contraction algorithms on a variety of synthetic problems on regular lattices and random regular graphs. We further showcase the power of the approach by demonstrating compressed contraction of tensor networks for frustrated three-dimensional lattice partition functions, dimer counting on random regular graphs, and to access the hardness transition of random tensor network models, in graphs with many thousands of tensors.