News

Poster on When Deep Learning Meets Nontrivial Constraints in the 3M Poster Session. (Jun 7, 2023)

Poster on When Deep Learning Meets Nontrivial Constraints in the Midwest ML Symposium (MMLS 2023). See our poster for more details! (May 16-17, 2023)

Tutorial on Deep Learning with Nontrivial Constraints in the SIAM International Conference on Data Mining (SDM23). See our slides for more details! (Apr 29, 2023)

M.S. final defense! Special thanks to my advisor Prof. Ju Sun! (Apr 7, 2023)

Paper release: Proud to release our paper Optimization and Optimizers for Adversarial Robustness on arXiv! We have created the first general-purpose method for evaluating adversarial robustness and challenged the reliability of the existing robustness evaluation and adversarial training frameworks. (Mar 24, 2023)

Paper acceptance: Our paper Implications of Solution Patterns on Adversarial Robustness has been accepted by Computer Vision and Pattern Recognition (CVPR) Workshop of Adversarial Machine Learning on Computer Vision: Art of Robustness! (Mar 22, 2023)

I am thrilled to join Prof. René Vidal’s group as a Computer and Information Science Ph.D. student at the University of Pennsylvania this Fall! (Feb 28, 2023)

Paper acceptance: Our paper Optimization for Robustness Evaluation beyond ℓp Metrics has been accepted by IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2023)! (Feb 16, 2023)

Service: To be a Reviewer for the 39th Conference on Uncertainty in Artificial Intelligence (UAI 2023). (Feb 4, 2023)

Tutorial: Our tutorial proposal Deep Learning with Nontrivial Constraints has been accepted to SIAM International Conference on Data Mining (SDM23) Tutorial Program as a two-hour tutorial! (Nov 10, 2022)

Paper acceptance: Our paper NCVX: A General-Purpose Optimization Solver for Constrained Machine and Deep Learning has been accepted by Neural Information Processing Systems (NeurIPS) Workshop on Optimization for Machine Learning (OPT 2022), see our poster for more details! (Oct 20, 2022)

Paper acceptance: Our paper Optimization for Robustness Evaluation beyond ℓp Metrics has been accepted by Neural Information Processing Systems (NeurIPS) Workshop on Optimization for Machine Learning (OPT 2022), see our poster for more details! (Oct 20, 2022)

Paper release: Proud to release our paper NCVX: A General-Purpose Optimization Solver for Constrained Machine and Deep Learning on arXiv! This is an expanded version of our previous announcement paper, with four detailed examples on constrained deep learning. (Oct 03, 2022)

Paper release: Proud to release our paper Optimization for Robustness Evaluation beyond ℓp Metrics on arXiv! This is a preview of our ongoing project that numerically solves adversarial attack problems with general metrics (vs SOTA that only deals with ℓ1, ℓ2, and ℓ∞), taking advantage of our NCVX framework. (Oct 03, 2022)

Service: To be a Reviewer for the 26th International Conference on Artificial Intelligence and Statistics (AISTATS 2023). (Sep 19, 2022)

Talk: We (speaker: Prof. Ju Sun) introduced NCVX PyGRANSO and its practical applications and tricks in the Nonsmooth Optimization in Machine Learning session in the International Conference on Continuous Optimization (ICCOPT), 2022. See the talk slides for more details! (Jul 27, 2022)

Code release: NCVX PyGRANSO v1.2.0 released. Check our Change Log here! (Jul 26, 2022)

Code release: NCVX PyGRANSO v1.1.0 released. Join our NCVX PyGRANSO Forum for more information! (Feb 20, 2022)

Media：Our NCVX package is highlighted in Research Computing (Office of the Vice President for Research). (Jan 07, 2022)

Code release：NCVX with its initial solver PyGRANSO v1.0.0 released. Check the documentation page and GitHub repo for more information. (Jan 01, 2022)

Paper release: Proud to release our paper NCVX: A User-Friendly and Scalable Package for Nonconvex Optimization in Machine Learning on arXiv! NCVX is the initial translation and revamping of the GRANSO package, with convenient features such as auto-differentiation and GPU support. In particular, NCVX can be used to solve constrained deep learning problems. (Nov 29, 2021)