This is a good contribution, with highly non-trivial theoretical results about the role of over-parameterization in tensor decomposition. Some reviewers are worried about the lack of numerical experiments and the weak connection to practical algorithms, but this is acceptable for papers with solid theoretical contribution at NeurIPS. The authors make it clear in the rebuttal that their goal is not develop an algorithm for neural networks. They also promised to add some numerical experiments. For these reasons, I recommend accept (poster).