
Gaussian discrepancy: a probabilistic relaxation of vector balancing
We introduce a novel relaxation of combinatorial discrepancy called Gaus...
read it

Averaging on the BuresWasserstein manifold: dimensionfree convergence of gradient descent
We study firstorder optimization algorithms for computing the barycente...
read it

Rejection sampling from shapeconstrained distributions in sublinear time
We consider the task of generating exact samples from a target distribut...
read it

The query complexity of sampling from strongly logconcave distributions in one dimension
We establish the first tight lower bound of Ω(loglogκ) on the query comp...
read it

Optimal dimension dependence of the MetropolisAdjusted Langevin Algorithm
Conventional wisdom in the sampling literature, backed by a popular diff...
read it

Efficient constrained sampling via the mirrorLangevin algorithm
We propose a new discretization of the mirrorLangevin diffusion and giv...
read it

Fast and Smooth Interpolation on Wasserstein Space
We propose a new method for smoothly interpolating probability measures ...
read it

SVGD as a kernelized Wasserstein gradient flow of the chisquared divergence
Stein Variational Gradient Descent (SVGD), a popular sampling algorithm,...
read it

Exponential ergodicity of mirrorLangevin diffusions
Motivated by the problem of sampling from illconditioned logconcave di...
read it

Gradient descent algorithms for BuresWasserstein barycenters
We study first order methods to compute the barycenter of a probability ...
read it

Online Absolute Ranking with Partial Information: A Bipartite Graph Matching Approach
Ever since the introduction of the secretary problem, the notion of sele...
read it
Sinho Chewi
is this you? claim profile