activity
20172023
most citedFrom Nesterov's Estimate Sequence to Riemannian Acceleration

15 citations · 44 across the 9 of their papers we have counts for

collaborators
Showing 2020Show all

6 papers · 1 filter

math.ST20208 cited

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…

math.ST2020

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…

cs.DS20201 cited

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…

math.OC202011 cited

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…

math.OC20201 cited

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

math.OC202015 cited

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…