Zhihua Zhang

Moreau--Yosida unadjusted Langevin sampling achieves $\widetilde O(\varepsilon^{-1})$ iterations for $\varepsilon$-accurate convergence to target distributions, bypassing the need for third derivatives.

Results demonstrate that MVM provides a direct single-field parameterization of stochastic reverse dynamics while maintaining competitive generation quality.

The leading last-iterate fluctuation in quantile temporal-difference learning can be controlled without polynomial dependence on the number of quantiles, challenging conventional assumptions about sample complexity.