Computational optimal transport: Complexity by accelerated gradient descent is better than by Sinkhorn's algorithm
P Dvurechensky, A Gasnikov… - … conference on machine …, 2018 - proceedings.mlr.press
We analyze two algorithms for approximating the general optimal transport (OT) distance
between two discrete distributions of size $ n $, up to accuracy $\varepsilon $. For the first …
between two discrete distributions of size $ n $, up to accuracy $\varepsilon $. For the first …
Scalable semidefinite programming
Semidefinite programming (SDP) is a powerful framework from convex optimization that has
striking potential for data science applications. This paper develops a provably correct …
striking potential for data science applications. This paper develops a provably correct …
A dual approach for optimal algorithms in distributed optimization over networks
We study dual-based algorithms for distributed convex optimization problems over networks,
where the objective is to minimize a sum Σ i= 1 mfi (z) of functions over in a network. We …
where the objective is to minimize a sum Σ i= 1 mfi (z) of functions over in a network. We …
Last-iterate convergent policy gradient primal-dual methods for constrained mdps
We study the problem of computing an optimal policy of an infinite-horizon discounted
constrained Markov decision process (constrained MDP). Despite the popularity of …
constrained Markov decision process (constrained MDP). Despite the popularity of …
Dropping convexity for faster semi-definite optimization
S Bhojanapalli, A Kyrillidis… - Conference on Learning …, 2016 - proceedings.mlr.press
We study the minimization of a convex function f (X) over the set of n\times n positive semi-
definite matrices, but when the problem is recast as\min_U g (U):= f (UU^⊤), with …
definite matrices, but when the problem is recast as\min_U g (U):= f (UU^⊤), with …
On the complexity of approximating Wasserstein barycenters
We study the complexity of approximating the Wasserstein barycenter of $ m $ discrete
measures, or histograms of size $ n $, by contrasting two alternative approaches that use …
measures, or histograms of size $ n $, by contrasting two alternative approaches that use …
Online adaptive methods, universality and acceleration
We present a novel method for convex unconstrained optimization that, without any
modifications ensures:(1) accelerated convergence rate for smooth objectives,(2) standard …
modifications ensures:(1) accelerated convergence rate for smooth objectives,(2) standard …
An inexact augmented Lagrangian framework for nonconvex optimization with nonlinear constraints
MF Sahin, A Alacaoglu, F Latorre… - Advances in Neural …, 2019 - proceedings.neurips.cc
We propose a practical inexact augmented Lagrangian method (iALM) for nonconvex
problems with nonlinear constraints. We characterize the total computational complexity of …
problems with nonlinear constraints. We characterize the total computational complexity of …
A universal algorithm for variational inequalities adaptive to smoothness and noise
We consider variational inequalities coming from monotone operators, a setting that
includes convex minimization and convex-concave saddle-point problems. We assume an …
includes convex minimization and convex-concave saddle-point problems. We assume an …
Online primal-dual mirror descent under stochastic constraints
We consider online convex optimization with stochastic constraints where the objective
functions are arbitrarily time-varying and the constraint functions are independent and …
functions are arbitrarily time-varying and the constraint functions are independent and …