← Search

Motahareh Sohrabi

2 accepted papers

2026

Accelerated and Stable Convergence with Anchored Generalized Optimistic Method

ICML 2026poster

We study first-order methods for solving monotone variational inequalities arising in min-max optimization. Classical approaches such as the extragradient method rely on two gradient queries per iteration, which limits their analysis and applicability in the online and stochastic settings. We propos…

Cited by 0SourceScholar
2024

On PI Controllers for Updating Lagrange Multipliers in Constrained Optimization

ICML 2024poster

Constrained optimization offers a powerful framework to prescribe desired behaviors in neural network models. Typically, constrained problems are solved via their min-max Lagrangian formulations, which exhibit unstable oscillatory dynamics when optimized using gradient descent-ascent. The adoption o…