LGR samples balanced treatment assignments in high-dimensional experiments via continuous relaxation and SGLD, retaining valid inference through randomization tests while being orders of magnitude faster than prior methods.
Zihao Yang, Tianyi Qu, and Xinran Li
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
stat.ME 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Introduces minimum free energy randomized design and dynamic allocation algorithm for RCTs to balance covariate control with randomization robustness via thermodynamic analogy.
citing papers explorer
-
Langevin-Gradient Rerandomization
LGR samples balanced treatment assignments in high-dimensional experiments via continuous relaxation and SGLD, retaining valid inference through randomization tests while being orders of magnitude faster than prior methods.
-
Minimum free energy randomized design to improve covariate balance
Introduces minimum free energy randomized design and dynamic allocation algorithm for RCTs to balance covariate control with randomization robustness via thermodynamic analogy.