arXiv cs.LG
· Papers
Wedge Sampling: Efficient Tensor Completion with Nearly-Linear Sample Complexity
arXiv:2602.05869v3 Announce Type: replace-cross Abstract: We introduce Wedge Sampling, a new non-adaptive sampling scheme for low-rank tensor completion. We study recovery of an order-$k$ low-rank tensor of dimension $ntimescdotstimes n$ from structured observations of its entries. Unlike the standard uniform entry