SOURCE-LINKED INTELLIGENCE

Sparse Data Augmentation for Optimization with Provable Guarantees

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

In nonconvex optimization problems arising in geometric machine learning, data augmentation is commonly used to promote invariance by averaging empirical losses over transformations of the data. Computing the fully augmented objective, however, requires access to every element of the transformation group $G$, which may be prohibitively expensive when $G$ is large or accessible only through sampling. We study whether full augmentation can instead be approximated using a small, fixed sample of transformations acquired before optimization and reused thereafter. Under suitable regularity condition

Read original source ↗ Open in workspace

recordType

paper

region

Global