Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Generalization at the Edge of Stability
Mario Tuci, Caner Korkmaz, Umut Şimşekli +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.LG2025
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…