Talks

Conference talks

  1. ICNONLA 2021 · Linearly-constrained nonsmooth optimization for training deep neural network. Chengdu, China, September 2021. [Slides]
  2. SIAM OP23 · An inexact augmented Lagrangian algorithm for training leaky ReLU neural network with group sparsity. Seattle, US, June 2023. [Slides]

    Organized session: Methods for constrained nonconvex problems with application to machine learning, with Ziyu He and Chuan He.

  3. MOPTA 2023 · First-order methods for affinely constrained composite non-convex non-smooth problems: Lower complexity bound and near-optimal methods. Lehigh University, US, August 2023. [Slides]
  4. INFORMS Annual Meeting 2023 · Decentralized methods for composite nonconvex strongly-concave minimax problems. Phoenix, US, October 2023.
  5. SIAM-NNP 2023 · Inexact proximal augmented Lagrangian method for weakly-convex problems with convex constraints. New Jersey Institute of Technology, Newark, NJ, US, October 2023. [Slides]

    Organized session: Large-scale structured optimization, with Mateo Diaz, Benjamin Grimmer, Jiaming Liang, and Yangyang Xu.

  6. INFORMS Conference on Optimization 2024 · Lower complexity bounds of first-order methods for affinely constrained composite nonconvex problems. Rice University, US, 2024.

    Organized session: Session SunC 4, with Negar Soheili.

  7. ISMP 2024 · A near-optimal method for quadratic constrained composite non-convex non-smooth problems. Montréal, Canada, July 2024.

    Organized session: Nonsmooth nonconvex optimization with geometric structure, with Douglas Soares Goncalves and Quentin Rebjock.

  8. ICCOPT 2025 · A single-loop SPIDER-type stochastic subgradient method for expectation-constrained nonconvex nonsmooth optimization. University of Southern California (University Park Main Campus), CA, US, July 2025.
  9. APORS Youth Forum 2025 · A SPIDER-type stochastic subgradient method for expectation-constrained nonconvex nonsmooth optimization. PolyU, Hong Kong, November 2025.

    Member of the organizing committee.

  10. International Workshop on Applied Mathematics + AI · Damped proximal augmented Lagrangian method for weakly-convex problems with convex constraints. PolyU, Hong Kong, December 2025.

    Member of the organizing committee.

  11. SIAM OP26 · A SPIDER-type stochastic subgradient method for expectation-constrained nonconvex nonsmooth optimization. University of Edinburgh, UK, June 2026.

Invited talks

  1. Beihang University · First-order methods for affinely constrained composite non-convex non-smooth problems: Lower complexity bound and near-optimal methods, October 2024. [Slides]
  2. The Hong Kong Polytechnic University · A stochastic smoothing framework for nonconvex-nonconcave min-sum-max problems with applications to Wasserstein distributionally robust optimization, April 2025.
  3. Wuhan University · A SPIDER-type stochastic subgradient method for expectation-constrained nonconvex nonsmooth optimization, March 2026. [Slides]
  4. Workshop on Young Researchers in Scientific and Engineering Computing. Hosted by LSEC, CAS, April 2026. [Slides]
  5. 第三届中国运筹学会数学规划分会青年学者论坛. Kunming, Yunnan, China, May 2026.
  6. Shanghai Jiao Tong University · A sequential smoothing majorant stochastic approximation method for nonconvex nonconcave minimax problems, September 2026.
  7. 中国运筹学会数学规划分会优化经纬（青年）论坛—第二期, October 2026 (scheduled).