Portrait de Motahareh Sohrabi

Motahareh Sohrabi

Collaborateur·rice de recherche - UdeM
Superviseur⋅e principal⋅e
Sujets de recherche
Apprentissage profond
Optimisation

Publications

Accelerated and Stable Convergence with Anchored Generalized Optimistic Method
We study first-order methods for solving monotone variational inequalities arising in min-max optimization. Classical approaches such as the… (voir plus) extragradient method rely on two gradient queries per iteration, which limits their analysis and applicability in the online and stochastic settings. We propose a family of Generalized Optimistic Methods with Anchoring (GOMA), which combine two time-scale optimistic updates with an anchoring term inspired by Halpern iteration. In particular, we show that for monotone Lipschitz operators, GOMA achieves an accelerated last-iterate convergence rate of
On PI Controllers for Updating Lagrange Multipliers in Constrained Optimization
Tianyue H. Zhang
Jose Gallego-Posada
Constrained optimization offers a powerful framework to prescribe desired behaviors in neural network models. Typically, constrained problem… (voir plus)s are solved via their min-max Lagrangian formulations, which exhibit unstable oscillatory dynamics when optimized using gradient descent-ascent. The adoption of constrained optimization techniques in the machine learning community is currently limited by the lack of reliable, general-purpose update schemes for the Lagrange multipliers. This paper proposes the
Weight-Sharing Regularization
Weight-sharing is ubiquitous in deep learning. Motivated by this, we propose a "weight-sharing regularization" penalty on the weights …