Follow
Ziye Ma
Ziye Ma
PhD Student at EECS, UC Berkeley
Verified email at berkeley.edu - Homepage
Title
Cited by
Cited by
Year
Tightened convex relaxations for neural network robustness certification
BG Anderson, Z Ma, J Li, S Sojoudi
2020 59th IEEE Conference on Decision and Control (CDC), 2190-2197, 2020
342020
Certifiably globally optimal extrinsic calibration from per-sensor egomotion
M Giamou, Z Ma, V Peretroukhin, J Kelly
IEEE Robotics and Automation Letters 4 (2), 367-374, 2019
302019
A sequential framework towards an exact SDP verification of neural networks
Z Ma, S Sojoudi
2021 IEEE 8th International Conference on Data Science and Advanced …, 2021
19*2021
Sharp restricted isometry property bounds for low-rank matrix recovery problems with corrupted measurements
Z Ma, Y Bi, J Lavaei, S Sojoudi
Proceedings of the AAAI Conference on Artificial Intelligence 36 (7), 7672-7681, 2022
112022
Semidefinite programming versus burer-monteiro factorization for matrix sensing
B Yalçın, Z Ma, J Lavaei, S Sojoudi
Proceedings of the AAAI Conference on Artificial Intelligence 37 (9), 10702 …, 2023
52023
Noisy low-rank matrix optimization: Geometry of local minima and convergence rate
Z Ma, S Sojoudi
International Conference on Artificial Intelligence and Statistics, 3125-3150, 2023
52023
Over-parametrization via lifting for low-rank matrix sensing: Conversion of spurious solutions to strict saddle points
Z Ma, I Molybog, J Lavaei, S Sojoudi
International Conference on Machine Learning, 23373-23387, 2023
32023
Geometric Analysis of Noisy Low-Rank Matrix Recovery in the Exact Parametrized and the Overparametrized Regimes
Z Ma, Y Bi, J Lavaei, S Sojoudi
INFORMS Journal on Optimization, 2023
32023
Partition-based convex relaxations for certifying the robustness of relu neural networks
BG Anderson, Z Ma, J Li, S Sojoudi
arXiv preprint arXiv:2101.09306, 2021
32021
Algorithmic Regularization in Tensor Optimization: Towards a Lifted Approach in Matrix Sensing
Z Ma, J Lavaei, S Sojoudi
Advances in Neural Information Processing Systems 36, 2024
12024
Towards optimal branching of linear and semidefinite relaxations for neural network robustness certification
BG Anderson, Z Ma, J Li, S Sojoudi
arXiv preprint arXiv:2101.09306, 2021
12021
Absence of spurious solutions far from ground truth: A low-rank analysis with high-order losses
Z Ma, Y Chen, J Lavaei, S Sojoudi
arXiv preprint arXiv:2403.06056, 2024
2024
Safety verification and robustness analysis of neural networks
B Anderson, J Li, Z Ma
2019
Supplementary Material for" Certifiably Globally Optimal Extrinsic Calibration from Per-Sensor Egomotion"
M Giamou, Z Ma, V Peretroukhin, J Kelly
2018
The system can't perform the operation now. Try again later.
Articles 1–14