To achieve robustness to adaptive adversaries, Bernoulli and reservoir sampling require sample size Ω(log |R| / ε²) instead of the static VC-dimension bound.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2019 2verdicts
UNVERDICTED 2representative citing papers
Experiments indicate deep learning models achieve higher accuracy on numerosity tasks for counts below human subitizing capacity.
citing papers explorer
-
The Adversarial Robustness of Sampling
To achieve robustness to adaptive adversaries, Bernoulli and reservoir sampling require sample size Ω(log |R| / ε²) instead of the static VC-dimension bound.
-
On the notion of number in humans and machines
Experiments indicate deep learning models achieve higher accuracy on numerosity tasks for counts below human subitizing capacity.