Search Results for author:
Found 14 papers, 1 papers with code
Extending the Reach of First-Order Algorithms for Nonconvex Min-Max Problems with Cohypomonotonicity
With a simple argument, we obtain optimal or best-known complexity guarantees with cohypomonotonicity or weak MVI conditions for $\rho < \frac{1}{L}$.
Complexity of Single Loop Algorithms for Nonlinear Programming with Stochastic Objective and Constraints
To find a point that satisfies $\varepsilon$-approximate first-order conditions, we require $\widetilde{O}(\varepsilon^{-3})$ complexity in the first case, $\widetilde{O}(\varepsilon^{-4})$ in the second case, and $\widetilde{O}(\varepsilon^{-5})$ in the third case.
Variance Reduced Halpern Iteration for Finite-Sum Monotone Inclusions
Our main contributions are variants of the classical Halpern iteration that employ variance reduction to obtain improved complexity guarantees in which $n$ component operators in the finite sum are ``on average'' either cocoercive or Lipschitz continuous and monotone, with parameter $L$.
Beyond the Golden Ratio for Variational Inequality Algorithms
We improve the understanding of the $\textit{golden ratio algorithm}$, which solves monotone variational inequalities (VI) and convex-concave min-max problems via the distinctive feature of adapting the step sizes to the local Lipschitz constants.
Convergence of First-Order Methods for Constrained Nonconvex Optimization with Dependent Data
As an application, we obtain first online nonnegative matrix factorization algorithms for dependent data based on stochastic projected gradient methods with adaptive step sizes and optimal rate of convergence.
On the Complexity of a Practical Primal-Dual Coordinate Method
We prove complexity bounds for the primal-dual algorithm with random extrapolation and coordinate descent (PURE-CD), which has been shown to obtain good practical performance for solving convex-concave min-max problems with bilinear coupling.
Convergence of adaptive algorithms for constrained weakly convex optimization
We analyze the adaptive first order algorithm AMSGrad, for solving a constrained stochastic optimization problem with a weakly convex objective.
Sample-efficient actor-critic algorithms with an etiquette for zero-sum Markov games
Our sample complexities also match the best-known results for global convergence of policy gradient and two time-scale actor-critic algorithms in the single agent setting.
Stochastic Variance Reduction for Variational Inequality Methods
We propose stochastic variance reduced algorithms for solving convex-concave saddle point problems, monotone variational inequalities, and monotone inclusions.
Random extrapolation for primal-dual coordinate descent
We introduce a randomly extrapolated primal-dual coordinate descent method that adapts to sparsity of the data matrix and the favorable structures of the objective function.
Conditional gradient methods for stochastically constrained convex minimization
We propose two novel conditional gradient-based methods for solving structured stochastic convex optimization problems with a large number of linear constraints.
Convergence of adaptive algorithms for weakly convex constrained optimization
We analyze the adaptive first order algorithm AMSGrad, for solving a constrained stochastic optimization problem with a weakly convex objective.
A new regret analysis for Adam-type algorithms
In this paper, we focus on a theory-practice gap for Adam and its variants (AMSgrad, AdamNC, etc.).
Smooth Primal-Dual Coordinate Descent Algorithms for Nonsmooth Convex Optimization
We propose a new randomized coordinate descent method for a convex optimization template with broad applications.
