← Search

Shira Vansover-Hager

2 accepted papers

2026

Flat Minima and Generalization: Insights from Stochastic Convex Optimization

ICML 2026poster

Understanding the generalization behavior of learning algorithms is a central goal of learning theory. A recently emerging explanation is that learning algorithms are successful in practice because they converge to flat minima, which have been consistently associated with improved generalization per…

Cited by 2SourceScholar
2025

Rapid Overfitting of Multi-Pass SGD in Stochastic Convex Optimization

ICML 2025spotlight

We study the out-of-sample performance of multi-pass stochastic gradient descent (SGD) in the fundamental stochastic convex optimization (SCO) model. While one-pass SGD is known to achieve an optimal $\Theta(1/\sqrt{n})$ excess population loss given a sample of size $n$, much less is understood abou…

Cited by 0SourcePDFScholar