Derives KL and TV error bounds for kTULA and tRLMC schemes, giving near-optimal ilde O(ε^{-1/2}) complexity for kTULA and ilde O(ε^{-1}) for tRLMC under log-Sobolev sampling.
Non-asymptotic convergence bounds for modified tamed unadjusted Langevin algorithm in non-convex setting
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Develops robust SGLD with non-asymptotic convergence bounds for non-convex DRO and applies it to neural network regression under adversarial corruption.
citing papers explorer
-
Error estimates for tamed Euler and Randomized Euler schemes for SDEs with locally Lipschitz drift with applications to non-logconcave sampling and optimization
Derives KL and TV error bounds for kTULA and tRLMC schemes, giving near-optimal ilde O(ε^{-1/2}) complexity for kTULA and ilde O(ε^{-1}) for tRLMC under log-Sobolev sampling.
-
Robust SGLD algorithm for solving non-convex distributionally robust optimisation problems
Develops robust SGLD with non-asymptotic convergence bounds for non-convex DRO and applies it to neural network regression under adversarial corruption.