2 papers
cs.LG2026
Decoupled Orthogonal Dynamics: Regularization for Deep Network Optimizers
Hao Chen, Jinghui Yuan, Hanmin Zhang
Is the standard weight decay in AdamW truly optimal? Although AdamW decouples weight decay from adaptive gradient scaling, a fundamental conflict remains: the Radial Tug-of-War. In…
cs.LG2025
SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming
Hong-Ming Chiu, Hao Chen, Huan Zhang +1
Neural network verifiers based on linear bound propagation scale impressively to massive models but can be surprisingly loose when neuron coupling is crucial. Conversely, semidefin…