Publications

Hengyue Liang, Buyun Liang, Le Peng, Ying Cui, Tim Mitchell, Ju Sun (2023). Optimization for Adversarial Robustness Evaluations and Implications from the Solution Patterns. Under review at International Journal of Computer Vision (IJCV).

Buyun Liang, Wenjie Zhang, Hengyue Liang, Tim Mitchell, Ying Cui, Ju Sun (2023). NCVX: A General-Purpose Optimization Solver for Machine Learning, and Practical Techniques. In preparation.

Website ICCOPT22 Slides SDM2023 Tutorial Proposal SDM 2023 slides MMLS 2023 Poster 3M Poster (2023)

Hengyue Liang, Buyun Liang, Le Peng, Ying Cui, Tim Mitchell, Ju Sun (2023). Implications of Solution Patterns on Adversarial Robustness. In Computer Vision and Pattern Recognition (CVPR) Workshop of Adversarial Machine Learning on Computer Vision (Art of Robustness).

Buyun Liang, Ryan de Vera, Hengyue Liang, Ying Cui, Tim Mitchell, Qizhi He, Ju Sun (2023). Neural Topology Optimization with Principled Constrained Optimization. In preparation for Structural and Multidisciplinary Optimization.

Buyun Liang, Tim Mitchell, Ju Sun (2022). NCVX: A General-Purpose Optimization Solver for Constrained Machine and Deep Learning. In Neural Information Processing Systems (NeurIPS) Workshop on Optimization for Machine Learning (OPT 2022).

Hengyue Liang, Buyun Liang, Ying Cui, Tim Mitchell, Ju Sun (2022). Optimization for Robustness Evaluation beyond ℓp Metrics. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2023) & Neural Information Processing Systems (NeurIPS) Workshop on Optimization for Machine Learning (OPT 2022).

Buyun Liang, Tim Mitchell, Ju Sun (2021). NCVX: A User-Friendly and Scalable Package for Nonconvex Optimization in Machine Learning. ArXiv preprint arXiv:2111.13984.

J. Ilja Siepmann, Jingyi L. Chen, Buyun Liang, Krishnan Mahesh (2020). Effect of Non-Condensable Gas on the Thermophysical Properties of Bubbly Water and on Bubble Collapse Dynamics Probed by Molecular Simulations. 33rd Symposium on Naval Hydrodynamics, Osaka, Japan, 18-23 October 2020.