Hancheng Min

Postdoctral Researcher, Electrical and Systems Engineering, University of Pennsylvania
Email: hanchmin [at] seas [dot] upenn [dot] edu

profile.png

I am Postdoc Researcher at Center for Innovation in Data Engineering and Science (IDEAS), University of Pennsylvania, advised by Prof. René Vidal. My research centers around building mathematical principles that facilitates the interplay between machine learning and dynamical systems, which combines tools in high dimensional probability, graph theory, dynamical system, control, and optimization.

Specifically, I am interested in utilizing data-driven methods to understand the dynamical behavior of large-scale and networked systems, as well as using learning-based control design for improving the performance of these systems while maintaining safe operation. In addition, I work on analyzing optimization algorithms in machine learning from a dynamical system point of view.

Prior to entering Penn, I received Ph.D. degree from Johns Hopkins University, where I am fortunate to be advised by Prof. Enrique Mallada and Prof. René Vidal. Before Hopkins, I received Master’s degree in Systems Engineering from University of Pennsylvannia and Bachelor’s degree in Automation from Tongji Univerisity, Shanghai.



News

Oct 25, 2024 One paper accepted to Automatica
May 1, 2024 One paper accepted to ICML
Jan 30, 2024 One paper accepted to PSCC
Jan 16, 2024 One paper accepted to ICLR
Nov 16, 2023 I gave a contributed talk at DeepMath 2023
Sep 30, 2023 I attended MoDL 2023 in NYC
Jul 24, 2023 I attended ICML2023 at Honolulu, Hawaii.
Jul 21, 2023 I defended my Ph.D. Thesis.
Jun 16, 2023 I attended L4DC2023 at Penn.
Jun 1, 2023 ACC talk at San Diego
Apr 25, 2023 One paper accepted to ICML
Mar 15, 2023 One paper accepted to L4DC
Jan 30, 2023 One paper accepted to AISTATS
Jan 20, 2023 ROSEI Summit for Sustainable Energy Research at JHU
Jan 7, 2023 One paper accepted to ACC
Jan 7, 2023 One paper accepted to TAC
Sep 30, 2022 I attended MoDL 2022 in NYC
Jun 30, 2022 RSRG Seminar at California Institute of Technology.
Jun 20, 2022 I attended the 4th Learning for Dynamics and Control Conference in Palo Alto, CA.
Jun 10, 2022 Semiautonomous seminar at University of Berkeley
Mar 30, 2022 Virtual talk at 2022 MINDS Retreat
Mar 7, 2022 One paper accepted to L4DC
Jan 12, 2022 Virtual talk at 2022 TRIPODS Winter School
Sep 30, 2021 I attended MoDL 2021 in NYC
Sep 12, 2021 Virtual talk at ICML 2021
Aug 15, 2021 I passed the GBO Exam at ECE department at Hopkins.
Jul 12, 2021 Virtual talk at ICML 2021
May 12, 2021 Virtual talk at ACC 2021
May 7, 2021 One paper accepted to ICML
Jan 15, 2021 I received MINDS Spring Fellowship 2021.
Nov 7, 2020 One paper accepted to L-CSS/ACC
Dec 6, 2019 CDC talk at Nice, France
Nov 15, 2019 I received MINDS Spring Fellowship 2020.
Jun 7, 2019 One paper accepted to CDC
Feb 1, 2019 I passed the departmental qualifying exam at ECE at Hopkins


Selected publications

  1. dir_flow.gif
    Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization
    Hancheng MinEnrique Mallada, and René Vidal
    In International Conference on Learning Representations (ICLR), May 2024
  2. coherence.gif
    A Frequency Domain Analysis of Slow Coherency in Networked Systems
    Hancheng MinRichard Pates, and Enrique Mallada
    Automatica, May 2024
    accepted
  3. lin_conv.png
    On the Convergence of Gradient Flow on Multi-layer Linear Models
    Hancheng MinRené Vidal, and Enrique Mallada
    In The 40th International Conference on Machine Learning (ICML), Jul 2023
  4. inter_area.gif
    Learning Coherent Clusters in Weakly-Connected Network Systems
    Hancheng Min, and Enrique Mallada
    In Proceedings of The 5th Annual Learning for Dynamics and Control Conference, Jun 2023
  5. safe_rl.png
    Learning to Act Safely with Limited Exposure and Almost Sure Certainty
    IEEE Transaction on Automatic Control, May 2023