Research
Research Interests
Publications (*=euqal contribution)
Exact Recovery Guarantees for Parameterized Non-linear System Identification Problem under Adversarial Attacks
Haixiang Zhang, Baturalp Yalcin, Javad Lavaei, Eduardo Sontag, submitted, 2024.
Exact Recovery for System Identification with More Corrupt Data than Clean Data
Baturalp Yalcin, Haixiang Zhang, Javad Lavaei, Murat Arcak, submitted, 2024.
Distributionally Robust Joint Chance-Constrained Optimal Power Flow using Relative Entropy
Haixiang Zhang*, Eli Brock*, Javad Lavaei, Somayeh Sojoudi, submitted, 2024.
Geometric Analysis of Matrix Sensing over Graphs
Haixiang Zhang, Ying Chen, Javad Lavaei, Conference on Neural Information Processing Systems (NeurIPS), 2023.
Stochastic Localization Methods for Convex Discrete Optimization via Simulation
Haixiang Zhang, Zeyu Zheng, Javad Lavaei, Operations Research, 2023.
Distributionally Robust Optimization for Nonconvex QCQPs with Stochastic Constraints
Haixiang Zhang*, Eli Brock*, Julie Mulvaney-Kemp, Javad Lavaei, Somayeh Sojoudi, Conference on Decision and Control (CDC), 2023.
A New Complexity Metric for Nonconvex Rank-one Generalized Matrix Completion
Haixiang Zhang, Baturalp Yalcin, Javad Lavaei, Somayeh Sojoudi, Mathematical Programming, 2023.
Gradient-based Algorithms for Convex Discrete Optimization via Simulation
Haixiang Zhang, Zeyu Zheng, Javad Lavaei, Operations Research, 2022.
Factorization Approach for Low-complexity Matrix Completion Problems: Exponential Number of Spurious Solutions and Failure of Gradient Methods
Baturalp Yalcin, Haixiang Zhang, Javad Lavaei, Somayeh Sojoudi, 25th International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.
Uniqueness of Power Flow Solutions Using Graph-theoretic Notions
Haixiang Zhang, SangWoo Park, Javad Lavaei, Ross Baldick, IEEE Transactions on Control of Network Systems, 2021.
Local and Global Linear Convergence of General Low-Rank Matrix Recovery Problems
Yingjie Bi, Haixiang Zhang, Javad Lavaei, Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022.
General Low-rank Matrix Optimization: Geometric Analysis and Sharper Bounds
Haixiang Zhang, Yingjie Bi, Javad Lavaei, Conference on Neural Information Processing Systems (NeurIPS), 2021.
Stochastic L-Convex Function Minimization
Haixiang Zhang, Zeyu Zheng, Javad Lavaei, Conference on Neural Information Processing Systems (NeurIPS), 2021.
On the Geometric Analysis of A Quartic-quadratic Optimization Problem under A Spherical Constraint
Haixiang Zhang, Andre Milzarek, Zaiwen Wen, Wotao Yin, Mathematical Programming, 2021.
A Dynamical System Perspective for Escaping Sharp Local Minima in Equality Constrained Optimization Problems
Han Feng, Haixiang Zhang, Javad Lavaei, Conference on Decision and Control (CDC), 2020.
Selection of the Best under Convexity
Haixiang Zhang, Zeyu Zheng, Javad Lavaei, technical report, 2021.
Talks
Session on ‘‘Efficient algorithms for non-convex low-rank matrix optimization problems’’
INFORMS Annual Meeting, Phoenix, AZ, October 2023
Minisymposium on ‘‘Recent Advances in Stochastic Optimization Methods for Machine Learning’’
SIAM Optimization Conference, Seattle, WA, June 2023
Guest lecture at ‘‘Numerical algorithms for nonlinear optimization and machine learning’’ course
Tsinghua-Berkeley Shenzhen Institute (TBSI), online, May 2023
Seminar of the Elite Program of Computational and Applied Math for Ph.D. Students
Peking University, Beijing, China, September 2022
Session on ‘‘Efficient algorithms for non-convex low-rank matrix optimization problems’’
INFORMS Annual Meeting, Indianapolis, IN, October 2022
Session on ‘‘Reaching global optimum in non-convex optimization problems’’
INFORMS Annual Meeting, Anaheim, CA, October 2021
Seminar of the Elite Program of Computational and Applied Math for Ph.D. Students
Peking University, Beijing, China, April 2019
Short talk at the Mathematical Programming Branch of Operation Society of China
Beihang University (BUAA), Beijing, China, September 2018
|