2 papers
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…
stat.ML2025
Exact Recovery of Sparse Binary Vectors from Generalized Linear Measurements
Arya Mazumdar, Neha Sangwan
We consider the problem of exact recovery of a -sparse binary vector from generalized linear measurements (such as logistic regression). We analyze the linear estimation algorit…