CO2 reduces coreset selection for any smooth divergence to MMD minimization and proves that Sinkhorn divergence coresets of size m=ω(log^d n) match the error of the full empirical measure.
Exact lower and upper bounds on the incomplete gamma function
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Lower and upper bounds $B_a(x)$ on the incomplete gamma function $\Gamma(a,x)$ are given for all real $a$ and all real $x>0$. These bounds $B_a(x)$ are exact in the sense that $B_a(x)\underset{x\downarrow0}\sim\Gamma(a,x)$ and $B_a(x)\underset{x\to\infty}\sim\Gamma(a,x)$. Moreover, the relative errors of these bounds are rather small for other values of $x$, away from $0$ and $\infty$.
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Coreset selection for the Sinkhorn divergence and generic smooth divergences
CO2 reduces coreset selection for any smooth divergence to MMD minimization and proves that Sinkhorn divergence coresets of size m=ω(log^d n) match the error of the full empirical measure.