Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Efficient Support Recovery of Mixtures of Sparse Linear Classifiers with Fewer Measurements
Xiaxin Li, Arya Mazumdar
The support recovery problem in mixture of linear classifiers aims to identify the features relevant to the underlying decision rules when data is generated by a mixture of several…
cs.LG2025
Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel
Yilan Chen, Zhichao Wang, Wei Huang +3
Gradient-based optimization methods have shown remarkable empirical success, yet their theoretical generalization properties remain only partially understood. In this paper, we est…