Publications

Preprints

• Proximal Oracles for Optimization and Sampling [pdf]
  

  • Jiaming Liang and Yongxin Chen, arXiv:2404.02239, 2024

• On Independent Samples Along the Langevin Diffusion and the Unadjusted Langevin Algorithm [pdf]
  

  • Jiaming Liang, Siddharth Mitra and Andre Wibisono, arXiv:2402.17067, 2024

• Variance Reduction and Low Sample Complexity in Stochastic Optimization via Proximal Point Method [pdf]
  

  • Jiaming Liang, arXiv:2402.08992, 2024

• Proximal bundle methods for hybrid weakly convex composite optimization problems [pdf]
  

  • Jiaming Liang, Renato D.C. Monteiro and Honghao Zhang, arXiv:2303.14896, 2023

• A Doubly Accelerated Inexact Proximal Point Method for Nonconvex Composite Optimization Problems [pdf]
  

  • Jiaming Liang and Renato D.C. Monteiro, arXiv:1811.11378, 2018

Journal Papers

• A single cut proximal bundle method for stochastic convex composite optimization [pdf]
  

  • Jiaming Liang, Vincent Guigues and Renato D.C. Monteiro

  • Mathematical Programming, 2023

• A Proximal Algorithm for Sampling [pdf]
  

  • Jiaming Liang and Yongxin Chen

  • Transactions on Machine Learning Research, 2023

• A unified analysis of a class of proximal bundle methods for solving hybrid convex composite optimization problems [pdf]
  

  • Jiaming Liang and Renato D.C. Monteiro

  • Mathematics of Operations Research, 2023

• Average Curvature FISTA for Nonconvex Smooth Composite Optimization Problems [pdf]
  

  • Jiaming Liang and Renato D.C. Monteiro

  • Computational Optimization and Applications, 86(1):275-302, 2023

• A Proximal Bundle Variant with Optimal Iteration-Complexity for a Large Range of Prox Stepsizes [pdf]
  

  • Jiaming Liang and Renato D.C. Monteiro

  • SIAM Journal on Optimization, 31(4):2955–2986, 2021

• A FISTA-type accelerated gradient algorithm for solving smooth nonconvex composite optimization problems [pdf]
  

  • Jiaming Liang, Renato D.C. Monteiro and Chee-Khian Sim

  • Computational Optimization and Applications, 79(3):649-679, 2021

• An Average Curvature Accelerated Composite Gradient Method for Nonconvex Smooth Composite Optimization Problems [pdf]
  

  • Jiaming Liang and Renato D.C. Monteiro

  • SIAM Journal on Optimization, 31(1):217-241, 2021

  • Alice and John Jarvis Ph.D. Student Paper Competition Honorable Mention, Georgia Tech ISyE, 2021

• Early Termination of Convex QP Solvers in Mixed-Integer Programming for Real-Time Decision Making [pdf]
  

  • Jiaming Liang, Stefano Di Cairano and Rien Quirynen

  • IEEE Control Systems Letters, 5(4):1417-1422, 2020

• Stability analysis for periodic solutions of the van der pol–duffing forced oscillator [pdf]
  

  • Jifeng Cui, Jiaming Liang and Zhiliang Lin

  • Physica Scripta, 91(1):015201, 2015

Conference Papers

• Nesterov smoothing for sampling without smoothness [pdf]
  

  • Jiaojiao Fan, Bo Yuan, Jiaming Liang, and Yongxin Chen

  • 2023 Conference on Decision and Control (CDC)

• On a Class of Gibbs Sampling over Networks [pdf]
  

  • Bo Yuan, Jiaojiao Fan, Jiaming Liang, Andre Wibisono, and Yongxin Chen

  • 2023 Conference on Learning Theory (COLT)

• A Proximal Algorithm for Sampling from Non-smooth Potentials [pdf]
  

  • Jiaming Liang and Yongxin Chen

  • 2022 Winter Simulation Conference (WSC)

• Early Termination of Convex QP Solvers in Mixed-Integer Programming for Real-Time Decision Making [pdf]
  

  • Jiaming Liang, Stefano Di Cairano and Rien Quirynen

  • 2021 American Control Conference (ACC)

• A FISTA-type average curvature accelerated composite gradient method for nonconvex optimization problems [pdf]
  

  • Jiaming Liang and Renato D.C. Monteiro

  • 12th OPT Workshop on Optimization for Machine Learning (OPT2020)

• Ship roll behaviour in large amplitude beam waves [pdf]
  

  • Jiaming Liang and Zhiliang Lin

  • International Conference on Ocean, Offshore and Arctic Engineering (OMAE 2015)

Patents

• Rien Quirynen, Jiaming Liang, and Stefano Di Cairano. Controller with Early Termination in Mixed-Integer Optimal Control Optimization. US Patent App. 17089763. 05/05/2022. [link]