3 papers
cs.LG2026
Conflicting Biases at the Edge of Stability: Norm versus Sharpness Regularization
Maria Matveev, Vit Fojtik, Hung-Hsu Chou +2
The remarkable generalization properties of overparameterized networks are often attributed to implicit biases, such as norm minimization at small learning rates and low sharpness…
math.OC2026
Stability of Low-Rank Implicit Regularization in Perturbed Deep Matrix Factorization
Jingzhe Wang, Hung-Hsu Chou
This paper studies the stability of low-rank implicit regularization in deep matrix factorization, a tractable model for understanding how gradient-based training can favor low-com…
cs.LG2026
GradPCA: Leveraging NTK Alignment for Reliable Out-of-Distribution Detection
Mariia Seleznova, Hung-Hsu Chou, Claudio Mayrink Verdun +1
We introduce GradPCA, an Out-of-Distribution (OOD) detection method that exploits the low-rank structure of neural network gradients induced by Neural Tangent Kernel (NTK) alignmen…