163 citations · 496 across the 40 of their papers we have counts for
8 papers · 1 filter
Curvature-Scaled Sharpness-Aware Minimization: Convergence Beyond Smoothness
Dimitris Oikonomou, Nicolas Loizou
Sharpness-Aware Minimization (SAM) has established itself as a widely used method for training deep neural networks. Despite its popularity, existing convergence guarantees for SAM…
Extragradient and Past Extragradient Methods for -Lipschitz Variational Inequalities
Ezra Greenberg, Nicolas Loizou
Variational inequalities (VIs) capture a broad class of optimization problems central to modern machine learning, including min-max optimization and equilibrium computation in mult…
Dual-Anchor Acceleration Is Near-Optimal for Stochastic Monotone Root-Finding
TaeHo Yoon, Nicolas Loizou
Among distinct optimal acceleration mechanisms for deterministic monotone root-finding problems and fixed-point problems, dual-anchoring has recently been shown to admit a more rob…
Polyak-Type Extragradient Methods for Monotone Root-Finding Problems
TaeHo Yoon, Sayantan Choudhury, Ezra Greenberg +1
We study Polyak-type step-size selection for extragradient methods for solving deterministic and stochastic monotone root-finding problems. We show that the known projection-type c…
Direct Acceleration of Stochastic Root-Finding Without Variance Reduction and Regularization
TaeHo Yoon, Nicolas Loizou
Acceleration for deterministic root-finding problems has been extensively studied in recent years; specifically, the anchor-based, or Halpern-type methods achieve optimal convergen…
On Same-Sample and Independent-Sample Stochastic Extragradient for Monotone Variational Inequalities
TaeHo Yoon, Nicolas Loizou
We study stochastic extragradient (SEG) methods for solving monotone variational inequality problems (VIPs) over a feasible set. Although extragradient is a foundational algorithm…
Adaptive Sharpness-Aware Minimization with a Polyak-type Step size: A Theory-Grounded Scheduler
Dimitris Oikonomou, Nicolas Loizou
Sharpness-Aware Minimization (SAM) has established itself as a powerful and widely adopted optimizer for training machine learning models. By explicitly minimizing the sharpness of…
Certified Robustness from Approximate Gaussian Mixture Structures in Pretrained Latent Spaces
Konstantinos Emmanouilidis, Tianjiao Ding, Nghia Nguyen +2
Deep learning models are vulnerable to adversarial perturbations, raising important concerns for safety-critical deployment. Empirical defenses can achieve strong robustness in pra…