3 papers
cs.LG2026
Generalization at the Edge of Stability
Mario Tuci, Caner Korkmaz, Umut ÅimÅekli +1
Training modern neural networks often relies on large learning rates, operating at the edge of stability, where the optimization dynamics exhibit oscillatory and chaotic behavior.…
cs.LG2026
Stability, Complexity and Data-Dependent Worst-Case Generalization Bounds
Mario Tuci, Lennart Bastian, Benjamin Dupuis +3
Providing generalization guarantees for stochastic optimization algorithms remains a key challenge in learning theory. Recently, numerous works demonstrated the impact of the geome…
stat.ML2025
Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping
Umut ÅimÅekli, Mert Gürbüzbalaban, Sinan Yıldırım +1
The injection of heavy-tailed noise into the iterates of stochastic gradient descent (SGD) has garnered growing interest in recent years due to its theoretical and empirical benefi…