Introduces entropy equivalence testing with a sample-efficient algorithm whose complexity is lower than standard closeness testing and applies it to improve closeness testing for low-degree Bayesian networks.
arXiv preprint arXiv:2002.11457 , year =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Defines empirical sensitivity and proves Ω(η + √(η d/n)) lower bound (tight up to logs) for any Gaussian mean estimator achieving optimal O(√(d/n)) ℓ₂ error.
Binary-detector Gaussian boson sampling is proposed for sample-efficient graph classification, with an investigation into its connection to the Torontonian matrix function.
citing papers explorer
-
Entropy Equivalence Testing
Introduces entropy equivalence testing with a sample-efficient algorithm whose complexity is lower than standard closeness testing and applies it to improve closeness testing for low-degree Bayesian networks.
-
Robust Statistical Estimators with Bounded Empirical Sensitivity
Defines empirical sensitivity and proves Ω(η + √(η d/n)) lower bound (tight up to logs) for any Gaussian mean estimator achieving optimal O(√(d/n)) ℓ₂ error.
-
Sample efficient graph classification using binary Gaussian boson sampling
Binary-detector Gaussian boson sampling is proposed for sample-efficient graph classification, with an investigation into its connection to the Torontonian matrix function.