My main interests have been in the intersection of three technical fields: optimization, dynamical systems and control, and machine learning. One of my recent focuses is on robust control and robust optimization using tools such as probability theory, functional analysis, learning/kernel methods. I believe robust optimization, with modern convex analysis and nonlinear programming, could play an interesting role in many cutting-edge applications in robust machine learning/reinforcement learning as well as in stochastic control.

Technical reports (grouped by topics)

Robustness and uncertainty in learning, optimization, and control

Kernel Distributionally Robust Optimization. Jia-Jie Zhu, Wittawat Jitkrittum, Moritz Diehl, Bernhard Schölkopf, 2020. Preprint. paper code

Worst-Case Risk Quantification under Distributional Ambiguity using Kernel Mean Embedding in Moment Problem. Jia-Jie Zhu, Wittawat Jitkrittum, Moritz Diehl, Bernhard Schölkopf, 2020. Preprint. paper

A Kernel Mean Embedding Approach to Reducing Conservativeness in Stochastic Programming and Control. Zhu, Jia-Jie, Moritz Diehl and Bernhard Schölkopf, L4DC 2020. In PMLR paper slides

A New Distribution-Free Concept for Representing, Comparing, and Propagating Uncertainty in Dynamical Systems with Kernel Probabilistic Programming. Zhu, Jia-Jie, Krikamol Muandet, Moritz Diehl, and Bernhard Schölkopf. To appear in IFAC 2020 paper slides

Robust Humanoid Locomotion Using Trajectory Optimization and Sample-Efficient Learning. Yeganegi, Mohammad Hasan, Majid Khadiv, S Ali A Moosavian, Jia-Jie Zhu, Andrea Del Prete, and Ludovic Righetti. IEEE Humanoids, 2019. paper

Generative Adversarial Active Learning. J.J. Zhu, J. Bento, 2017. Teaching Machines, Robots, and Humans Workshop, NIPS 2017. paper

Learning for control in hybrid systems

Fast Non-Parametric Learning to Accelerate Mixed-Integer Programming for Online Hybrid Model Predictive Control. Zhu, Jia-Jie, and Martius, Georg. To appear in IFAC 2020 paper slides

Control What You Can: Intrinsically Motivated Task-Planning Agent. Blaes, Sebastian, Marin Vlastelica Pogančić, JJ Zhu, and Georg Martius. NeurIPS, 2019. paper

Deep Reinforcement Learning for Resource-Aware Control. D. Baumann, J.J. Zhu, G. Martius, S. Trimpe, 2018. IEEE CDC 2018. paper code

Numerical methods & optimization

Projection Algorithms for Non-Convex Minimization with Application to Sparse Principal Component Analysis. J.J. Zhu, D. Phan, W. Hager, 2015. Journal of Global Optimization. paper code

A Metric for Sets of Trajectories that is Practical and Mathematically Consistent. J. Bento, J.J. Zhu, 2016. paper

A Decentralized Multi-Block Algorithm for Demand-Side Primary Frequency Control Using Local Frequency Measurements. J. Brooks, W. Hager, J.J. Zhu, 2015. paper