Double-Loop Unadjusted Langevin Algorithm
A well-known first-order method for sampling from log-concave probability distributions is the Unadjusted Langevin Algorithm (ULA). This work proposes a new annealing step-size schedule for ULA, which allows to prove new convergence guarantees for sampling from a smooth log-concave distribution, which are not covered by existing state-of-the-art convergence guarantees. To establish this result, we derive a new theoretical bound that relates the Wasserstein distance to total variation distance between any two log-concave distributions that complements the reach of Talagrand $T_2$ inequality. Moreover, applying this new step size schedule to an existing constrained sampling algorithm, we show state-of-the-art convergence rates for sampling from a constrained log-concave distribution, as well as improved dimension dependence.
final_icml.pdf
Publisher's version
openaccess
305.78 KB
Adobe PDF
52fee2f65b31b39ed75fea5883a8785d
final_icml_supp.pdf
Publisher's version
openaccess
448.06 KB
Adobe PDF
3b2b024be20335224658f1eae91d9ee3