Fotografi av Chuan He

Chuan He

Biträdande universitetslektor

Jag är biträdande universitetslektor vid avdelningen Tillämpad matematik (TIMA) och är även knuten till WASP vid Linköpings universitet. Jag arbetar med kontinuerlig optimering, maskininlärning och deras skärningspunkt.

Synergier mellan optimering och datavetenskap

Mina forskningsintressen kretsar kring datavetenskap och optimering, med ämnen som djupinlärning, decentraliserad optimering, storskalig optimering och högre ordningens metoder.

Jag är också intresserad av tillämpningar av maskininlärning inom sjukvård, vetenskaplig beräkning, bildvetenskap och ingenjörsvetenskap.

Innan jag började på LiU avlade jag min doktorsexamen vid University of Minnesota. Jag tog min grundexamen vid Xiamen University.

Kortfattat CV (på engelska)

Employment

  • Assistant Professor in Optimization, Linköping University, Linköping, Sweden
    September 2024 - Present
  • Postdoctoral Associate in Computer Science and Engineering, University of Minnesota, Minneapolis, USA
    Supervisor: Professor Ju Sun
    Oct 2023 – July 2024

Education

  • Ph.D. in Industrial and Systems Engineering, University of Minnesota Minneapolis, USA
    Advisor: Professor Zhaosong Lu
    Sep 2019 – Sep 2023
  • B.S. in School of Mathematical Sciences, Xiamen University Xiamen, China
    Supervisor: Professor Wen Huang
    Sep 2015 – July 2019

Conference activities

Presentations

  1. “Newton-CG Methods under H¨older Conditions”
    - INFORMS Annual Meeting, Seattle, USA, Oct 2024.
  2. “Augmented Lagrangian Methods for Constrained Optimization in Machine Learning”
    - INFORMS Annual Meeting, Phoenix, USA, Oct 2023.
  3. “Second-Order Learning via Newton-CG Based Methods”
    - Applied Math conference, Shenzhen University, Shenzhen, China, July 2023.
    - SIAM Conference on Optimization, Seattle, USA, June 2023.
    - Applied Math Seminar, Southern University of Science and Technology, Shenzhen, China, May 2021.
  4. “Decision Rule Approaches for Bilevel Linear Programs”
    - INFORMS Annual Meeting, Virtual presentation, Nov 2020.

Conference activities 

Posters

  1. “Federated Learning with Convex Constraints”
    - NeurIPS OPT Workshop, New Orleans, USA, Dec 2023.
  2. “Novel Algorithms for Nonconvex Second-Order Optimization with Performance Guarantees”
    - Workshop on Continuous Optimization, Foundation of Computational Mathematics (FoCM) Conference, Paris, France, June 2023.

 

More information about me: 

https://chuanhe97.github.io/

 

Forskning

Publikationer

2024

Chuan He, Heng Huang, Zhaosong Lu (2024) A Newton-CG based barrier-augmented Lagrangian method for general nonconvex conic optimization Computational optimization and applications (Artikel i tidskrift) Vidare till DOI
  • Chuan He, Le Peng, Ju Sun, “Federated learning with convex global and local constraints”, Transactions on Machine Learning Research, 2024.
  • Akshit Goyal, Yiling Zhang, Chuan He, “Decision rule approaches for pessimistic bilevel linear programs under moment ambiguity with facility location applications”, INFORMS Journal on Computing, 35(6):1342-1360, 2023.
  • Masaru Ito, Zhaosong Lu, Chuan He, “A parameter-free conditional gradient method for composite minimization under H¨older condition”, Journal of Machine Learning Research, 24(166):1-34, 2023.
  • Chuan He, Zhaosong Lu, “A Newton-CG based barrier method for finding a second-order stationary point of nonconvex conic optimization with complexity guarantees”, SIAM Journal on Optimization, 33(2):1191–1222, 2023.
  • Chuan He, Zhaosong Lu, Ting Kei Pong, “A Newton-CG based augmented Lagrangian method for finding a second-order stationary point of nonconvex equality constrained optimization with complexity guarantees”, SIAM Journal on Optimization, 33(3):1734-1766, 2023.

Organisation