11 papers
Stochastic Dynamic Barrier Perturbed Gradient Methods for Nonconvex Simple Bilevel Optimization
Mohammad Mahdi Ahmadi, Jincheng Cao, Aryan Mokhtari +1
We study stochastic simple bilevel optimization with smooth, possibly nonconvex upper- and lower-level objectives accessed only through stochastic gradient oracles. A key challenge…
On the Analysis of Misspecified Variational Inequalities with Nonlinear Constraints
Novel Kumar Dey, Mohammad Mahdi Ahmadi, Erfan Yazdandoost Hamedani +1
In this paper, we study a class of misspecified variational inequalities (VIs) where both the monotone operator and nonlinear convex constraints depend on an unknown parameter lear…
Semi-infinite Nonconvex Constrained Min-Max Optimization
Cody Melcher, Zeinab Alizadeh, Lindsey Hiett +2
Semi-Infinite Programming (SIP) has emerged as a powerful framework for modeling problems with infinite constraints, however, its theoretical development in the context of nonconve…
Linear Convergence of a Unified Primal--Dual Algorithm for Convex--Concave Saddle Point Problems with Quadratic Growth
Cody Melcher, Afrooz Jalilzadeh, Erfan Yazdandoost Hamedani
In this paper, we study saddle point (SP) problems, focusing on convex-concave optimization involving functions that satisfy either two-sided quadratic functional growth (QFG) or t…
Simultaneous Learning and Optimization via Misspecified Saddle Point Problems
Mohammad Mahdi Ahmadi, Erfan Yazdandoost Hamedani
We study a class of misspecified saddle point (SP) problems, where the optimization objective depends on an unknown parameter that must be learned concurrently from data. Unlike ex…
A Randomized Block-Coordinate Primal-Dual Method for Large-scale Stochastic Saddle Point Problems
Erfan Yazdandoost Hamedani, Afrooz Jalilzadeh, Necdet Serhat Aybat
We consider (stochastic) convex-concave saddle point (SP) problems with high-dimensional decision variables, arising in various applications including machine learning problems. To…