Spectral gap-based deterministic tensor completion
KD Harris, O López, A Read… - … Conference on Sampling …, 2023 - ieeexplore.ieee.org
Tensor completion is a core machine learning algorithm used in recommender systems and
other domains with missing data. While the matrix case is well-understood, theoretical …
other domains with missing data. While the matrix case is well-understood, theoretical …
Strong consistency guarantees for clustering high-dimensional bipartite graphs with the spectral method
G Braun - Electronic Journal of Statistics, 2024 - projecteuclid.org
We investigate the problem of clustering bipartite graphs using a simple spectral method
within the framework of the Bipartite Stochastic Block Model (BiSBM), a popular model for …
within the framework of the Bipartite Stochastic Block Model (BiSBM), a popular model for …
Tensor Deli: Tensor Completion for Low CP-Rank Tensors via Random Sampling
We propose two provably accurate methods for low CP-rank tensor completion-one using
adaptive sampling and one using nonadaptive sampling. Both of our algorithms combine …
adaptive sampling and one using nonadaptive sampling. Both of our algorithms combine …
Non-backtracking eigenvector delocalization for random regular graphs
X Zhu, Y Zhu - arXiv preprint arXiv:2312.03300, 2023 - arxiv.org
The non-backtracking operator of a graph is a powerful tool in spectral graph theory and
random matrix theory. Most existing results for the non-backtracking operator of a random …
random matrix theory. Most existing results for the non-backtracking operator of a random …