Publications

My Google Scholar Profile

• X. Guo, F. Yu, H. Zhang, L. Qin, and B. Hu, COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability, International Conference on Machine Learning (ICML), 2024.
  

• A. Havens, A. Araujo, H. Zhang, and B. Hu, Fine-grained Local Sensitivity Analysis of Standard Dot-Product Self-Attention, International Conference on Machine Learning (ICML), 2024.
  

• Z. Wang*, B. Hu*, A. Havens, A. Araujo, Y. Zheng, Y. Chen, S. Jha, On the Scalability and Memory Efficiency of Semidefinite Programs for Lipschitz Constant Estimation of Neural Networks, International Conference on Learning Representations (ICLR), 2024. (*Equal contribution)
  

• P. Pauli, A. Havens, A. Araujo, S. Garg, F. Khorrami, F. Allgöwer, and B. Hu, Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations, International Conference on Learning Representations (ICLR), 2024.
  

• A. Havens, A. Araujo, S. Garg, F. Khorrami, and B. Hu, Exploiting Connections between Lipschitz Structures for Certifiably Robust Deep Equilibrium Models, NeurIPS, 2023.
  

• X. Guo, D. Keivan, G. Dullerud, P. Seiler, and B. Hu, Complexity of Derivative-Free Policy Optimization for Structured H-Infinity Control, NeurIPS, 2023.
  

• H. Xue, A. Araujo, B. Hu, and Y. Chen, Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability, NeurIPS, 2023.
  

• X. Zhang, B. Hu, and T. Basar, Learning the Kalman Filter with Fine-Grained Sample Complexity, American Control Conference (ACC), 2023.
  

• A. Araujo, A. Havens, B. Delattre, A. Allauzen, and B. Hu, A Unified Algebraic Perspective on Lipschitz Neural Networks, International Conference on Learning Representations (ICLR), 2023. (Spotlight)
  

• B. Hu, K. Zhang, N. Li, M. Mesbahi, M. Fazel, and T. Basar, Toward a Theoretical Foundation of Policy Optimization for Learning Control Policies, Annual Review of Control, Robotics, and Autonomous Systems, 2023.
  

• X. Guo and B. Hu, Global Convergence of Direct Policy Search for State-Feedback H-Infinity Robust Control: A Revisit of Nonsmooth Synthesis with Goldstein Subdifferential, NeurIPS, 2022.
  

• B. Hu and Y. Zheng, Connectivity of the Feasible and Sublevel Sets of Dynamic Output Feedback Control with Robustness Constraints, IEEE Control Systems Letters, 2022.
  

• A. Havens, D. Keivan, P. Seiler, G. Dullerud, and B. Hu, Revisiting PGD Attacks for Stability Analysis of High-Dimensional Nonlinear Systems and Perception-Based Control, IEEE Control System Letters, 2022.
  

• J.K. Wang, C.H. Lin, A. Wibisono, and B. Hu, Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-Lojasiewicz Functions when the Non-Convexity is Averaged-Out, International Conference on Machine Learning (ICML), 2022.
  

• J.P. Jansch-Porto, B. Hu, and G. Dullerud, Policy Optimization for Markovian Jump Linear Quadratic Control: Gradient Method and Global Convergence, Accepted to IEEE Transactions on Automatic Control, 2022.
  

• X. Guo and B. Hu, Exact Formulas for Finite-Time Estimation Errors of Decentralized Temporal Difference Learning with Linear Function Approximation, arxiv, 2022.
  

• X. Guo and B. Hu, Convex Programs and Lyapunov Functions for Reinforcement Learning: A Unified Perspective on the Analysis of Value-Based Methods, American Control Conference (ACC), 2022.
  

• A. Havens, D. Keivan, P. Seiler, G. Dullerud, and B. Hu, Model-Free μ Synthesis via Adversarial Reinforcement Learning, American Control Conference (ACC), 2022.
  

• K. Zhang, X. Zhang, B. Hu, and T. Basar, Derivative-Free Policy Optimization for Linear Risk-Sensitive and Robust Control Design: Implicit Regularization and Sample Complexity, NeurIPS, 2021.
  

• A. Havens and B. Hu, On Imitation Learning of Linear Control Policies: Enforcing Stability and Robustness Constraints via LMI Conditions, American Control Conference (ACC), 2021.
  

• K. Zhang, B. Hu, and T. Basar, On the Stability and Convergence of Robust Adversarial Reinforcement Learning: A Case Study on Linear Quadratic Systems, NeurIPS, 2020.
  

• J.P. Jansch-Porto, B. Hu, and G. Dullerud, Policy Learning of MDPs with Mixed Continuous/Discrete Variables: A Case Study on Model-Free Control of Markovian Jump Systems, L4DC, 2020.
  

• B. Hu, P. Seiler, and L. Lessard, Analysis of Biased Stochastic Gradient Descent Using Sequential Semidefinite Programs, Mathematical Programming, 2020.
  

• J.P. Jansch-Porto, B. Hu, and G. Dullerud, Convergence Guarantees of Policy Optimization Methods for Markovian Jump Linear Systems, American Control Conference (ACC), 2020.
  

• H. Xiong, Y. Chi, B. Hu, and W. Zhang, Analytical Convergence Regions of Accelerated Gradient Descent in Nonconvex Optimization under Regularity Condition, Automatica, 2020.
  

• K. Zhang, B. Hu, and T. Basar, Policy Optimization for H2 Linear Control with H-infinity Robustness Guarantee: Implicit Regularization and Global Convergence, arxiv, 2019. (A conference version of the above paper has been accepted to L4DC 2020 and selected as one of 14/131 papers for oral presentation. The journal version of the paper has been accepted to SIAM Journal on Control and Optimization (SICON).)
  

• B. Hu and U. Syed, Characterizing the Exact Behaviors of Temporal Difference Learning Algorithms Using Markov Jump Linear System Theory, NeurIPS, 2019.
  

• D. Ding, B. Hu, N. Dhingra, and M. Jovanovic, An Exponentially Convergent Primal-Dual Algorithm for Nonsmooth Composite Minimization, IEEE Conference on Decision and Control (CDC), 2018.
  

• B. Hu, S. Wright, and L. Lessard, Dissipativity Theory for Accelerating Stochastic Variance Reduction: A Unified Analysis of SVRG and Katyusha Using Semidefinite Programs, International Conference on Machine Learning (ICML), 2018.
  

• S. Cyrus, B. Hu, B. Van Scoy, and L. Lessard, A Robust Accelerated Optimization Algorithm for Strongly Convex Functions, American Control Conference (ACC), 2018.
  

• A. Sundararajan, B. Hu, and L. Lessard, Robust Convergence Analysis of Distributed Optimization Algorithms, 55th Annual Allerton Conference on Communication, Control, and Computing, 2017.
  

• B. Hu and L. Lessard, Dissipativity Theory for Nesterov’s Accelerated Method, International Conference on Machine Learning (ICML), 2017.
  

• B. Hu, P. Seiler, and A. Rantzer, A Unified Analysis of Stochastic Optimization Methods Using Jump System Theory and Quadratic Constraints, Conference on Learning Theory (COLT), 2017.
  

• B. Hu and L. Lessard, Control Interpretations for First-Order Optimization Methods, American Control Conference (ACC), 2017.
  

• B. Hu, M.J. Lacerda, and P. Seiler, Robustness Analysis of Uncertain Discrete‐Time Systems with Dissipation Inequalities and Integral Quadratic Constraints, International Journal of Robust and Nonlinear Control, 2016.
  

• B. Hu and P. Seiler, Exponential Decay Rate Conditions for Uncertain Linear Systems Using Integral Quadratic Constraints, IEEE Transactions on Automatic Control, 2016.
  

• B. Hu and P. Seiler, Pivotal Decomposition for Reliability Analysis of Fault Tolerant Control Systems on Unmanned Aerial Vehicles, Reliability Engineering & System Safety, 2015.
  

• B. Hu and P. Seiler, A Probabilistic Method for Certification of Analytically Redundant Systems, International Journal of Applied Mathematics and Computer Science, 2015.
  

• B. Hu and P. Seiler, Worst-Case False Alarm Analysis of Fault Detection Systems, American Control Conference (ACC), 2014.
  

• B. Hu and P. Seiler, Certification Analysis for a Model-Based UAV Fault Detection System, AIAA Guidance, Navigation, and Control Conference, 2014.
  

• B. Hu and P. Seiler, Probability Bounds for False Alarm Analysis of Fault Detection Systems , 51st Annual Allerton Conference on Communication, Control, and Computing, 2013.