The paper proves polynomial mixing time upper bounds for three data augmentation algorithms (ProbitDA, LogitDA, LassoDA) with explicit dependence on design matrix, prior, n, and d.
Klartag, Logarithmic bounds for isoperimetry and slices of convex se ts, preprint, 2023
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2024 2verdicts
UNVERDICTED 2representative citing papers
In dimension two the authors prove Blocki's conjectures on Bergman kernels together with the L^p-Mahler conjectures for 1 ≤ p ≤ ∞ and supply an elementary proof of Bourgain's strong hyperplane conjecture.
citing papers explorer
-
Fast Mixing of Data Augmentation Algorithms: Bayesian Probit, Logit, and Lasso Regression
The paper proves polynomial mixing time upper bounds for three data augmentation algorithms (ProbitDA, LogitDA, LassoDA) with explicit dependence on design matrix, prior, n, and d.
-
Two-dimensional B\l{}ocki, $L^p$-Mahler, and Bourgain conjectures
In dimension two the authors prove Blocki's conjectures on Bergman kernels together with the L^p-Mahler conjectures for 1 ≤ p ≤ ∞ and supply an elementary proof of Bourgain's strong hyperplane conjecture.