2 citations · 2 across the 5 of their papers we have counts for
5 papers
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…
Well-conditioned Primal-Dual Interior-point Method for Accurate Low-rank Semidefinite Programming
Hong-Ming Chiu, Richard Y. Zhang
We describe how the low-rank structure in an SDP can be exploited to reduce the per-iteration cost of a convex primal-dual interior-point method down to time and $O(n^{2…
Fast and Accurate Estimation of Low-Rank Matrices from Noisy Measurements via Preconditioned Non-Convex Gradient Descent
Gavin Zhang, Hong-Ming Chiu, Richard Y. Zhang
Non-convex gradient descent is a common approach for estimating a low-rank ground truth matrix from noisy measurements, because it has per-iteration costs as low as $O(…
Tight Certification of Adversarially Trained Neural Networks via Nonconvex Low-Rank Semidefinite Relaxations
Hong-Ming Chiu, Richard Y. Zhang
Adversarial training is well-known to produce high-quality neural network models that are empirically robust against adversarial perturbations. Nevertheless, once a model has been…
Accelerating SGD for Highly Ill-Conditioned Huge-Scale Online Matrix Completion
Gavin Zhang, Hong-Ming Chiu, Richard Y. Zhang
The matrix completion problem seeks to recover a ground truth matrix of low rank from observations of its individual elements. Real-world matrix completion is…