Introduces the binning semiring and causal graphical models to show that correlational evaluation of learnability in formal language tasks leads to incorrect conclusions from confounders.
An efficient method for generating discrete random variables with general distributions
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A new sampler for discrete distributions using coin flips that combines linearithmic space, negligible runtime overhead, and entropy-optimal expected flips in [H(P), H(P)+2).
citing papers explorer
-
Causally Evaluating the Learnability of Formal Language Tasks
Introduces the binning semiring and causal graphical models to show that correlational evaluation of learnability in formal language tasks leads to incorrect conclusions from confounders.
-
Efficient Rejection Sampling in the Entropy-Optimal Range
A new sampler for discrete distributions using coin flips that combines linearithmic space, negligible runtime overhead, and entropy-optimal expected flips in [H(P), H(P)+2).