Local search with random Gaussian acceptance thresholds provably recovers planted sparse tensor signals down to the conjectured algorithmic threshold in several sparsity regimes.
Reducibility and computational lower bounds for problems with planted sparse structure
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.ST 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Almost-Optimal Local-Search Methods for Sparse Tensor PCA
Local search with random Gaussian acceptance thresholds provably recovers planted sparse tensor signals down to the conjectured algorithmic threshold in several sparsity regimes.