15 citations · 44 across the 9 of their papers we have counts for
6 papers · 1 filter
Optimal dimension dependence of the Metropolis-Adjusted Langevin Algorithm
Sinho Chewi, Chen Lu, Kwangjun Ahn +3
Conventional wisdom in the sampling literature, backed by a popular diffusion scaling limit, suggests that the mixing time of the Metropolis-Adjusted Langevin Algorithm (MALA) scal…
Efficient constrained sampling via the mirror-Langevin algorithm
Kwangjun Ahn, Sinho Chewi
We propose a new discretization of the mirror-Langevin diffusion and give a crisp proof of its convergence. Our analysis uses relative convexity/smoothness and self-concordance, id…
A simpler strong refutation of random -XOR
Kwangjun Ahn
Strong refutation of random CSPs is a fundamental question in theoretical computer science that has received particular attention due to the long-standing gap between the informati…
SGD with shuffling: optimal rates without component convexity and large epoch requirements
Kwangjun Ahn, Chulhee Yun, Suvrit Sra
We study without-replacement SGD for solving finite-sum optimization problems. Specifically, depending on how the indices of the finite-sum are shuffled, we consider the RandomShuf…
On Tight Convergence Rates of Without-replacement SGD
Kwangjun Ahn, Suvrit Sra
For solving finite-sum optimization problems, SGD without replacement sampling is empirically shown to outperform SGD. Denoting by the number of components in the cost and …
From Nesterov's Estimate Sequence to Riemannian Acceleration
Kwangjun Ahn, Suvrit Sra
We propose the first global accelerated gradient method for Riemannian manifolds. Toward establishing our result we revisit Nesterov's estimate sequence technique and develop an al…