7 papers
Auto-Conditioned Frank-Wolfe Algorithms
Khanh-Hung Giang-Tran, Soroosh Shafiee, Nam Ho-Nguyen
Frank-Wolfe methods are projection-free algorithms for constrained optimization whose practical performance often depends critically on the choice of step size. Classical closed-lo…
Chebyshev Center-Based Direction Selection for Multi-Objective Optimization and Training PINNs
Hoyeol Yoon, Seoungbin Bae, Nam Ho-Nguyen +1
Physics-informed neural networks (PINNs) are a promising approach for solving partial differential equations (PDEs). Their training, however, is often difficult because multiple lo…
Convergence, Duality and Well-Posedness in Convex Bilevel Optimization
Khanh-Hung Giang-Tran, Nam Ho-Nguyen, Fatma Kılınç-Karzan +1
We consider the convex bilevel optimization problem, also known as simple bilevel programming. There are two challenges in solving convex bilevel optimization problems. Firstly, st…
Conditional Gradient Methods with Standard LMO for Stochastic Simple Bilevel Optimization
Khanh-Hung Giang-Tran, Soroosh Shafiee, Nam Ho-Nguyen
We propose efficient methods for solving stochastic simple bilevel optimization problems with convex inner levels, where the goal is to minimize an outer stochastic objective funct…
Mistake, Manipulation and Margin Guarantees in Online Strategic Classification
Lingqing Shen, Nam Ho-Nguyen, Khanh-Hung Giang-Tran +1
We consider an online strategic classification problem where each arriving agent can manipulate their true feature vector to obtain a positive predicted label, while incurring a co…
A Projection-Free Method for Solving Convex Bilevel Optimization Problems
Khanh-Hung Giang-Tran, Nam Ho-Nguyen, Dabeen Lee
When faced with multiple minima of an "inner-level" convex optimization problem, the convex bilevel optimization problem selects an optimal solution which also minimizes an auxilia…