Research

• [arXiv] [code]

  Strongly-polynomial time and validation analysis of policy gradient methods

  
  Caleb Ju and Guanghui Lan (α)
  Submitted
• [arXiv] [code]

  Policy optimization over general state and action spaces

  
  Caleb Ju and Guanghui Lan (α)
  Submitted
• [arXiv] [code]

  Learning a Local Trading Strategy: Deep Reinforcement Learning for Grid-scale Renewable Energy Integration

  
  Caleb Ju and Constance Crozier
  Hawaii International Conference on System Sciences 2025
• [CE] [RS]

  Reinforcement Learning-Based Control for Waste Biorefining Processes Under Uncertainty

  
  Ji Gao, Abigael Whalen, Caleb Ju, Yongsheng Chen, Guanghui Lan, Zhaohui Tong
  Communications Engineering
• [arXiv] [code]

  Dual dynamic programming for stochastic programs over an infinite horizon

  
  Caleb Ju and Guanghui Lan
  Working paper
• [arXiv] [code]

  A model-free first-order method for linear quadratic regulator with Õ(1/ε) sampling complexity

  
  Caleb Ju, Georgios Kotsalis, Guanghui Lan
  Accepted to SIAM Journal on Control and Optimization
• [arXiv]

  Efficient parallel implementation of the multiplicative weight update method for graph-based linear programs

  
  Caleb Ju, Serif Yesil, Mengyuan Sun, Chandra Chekuri, Edgar Solomonik
  Pre-print
• [arXiv]

  Implicit regularization of Bregman proximal point algorithm and mirror descent on separable data

  
  Yan Li, Caleb Ju, Ethan X. Fang, Tuo Zhao
  Pre-print
• [FoCM] [arXiv]

  Communication lower bounds for nested bilinear algorithms via rank expansion of Kronecker products

  
  Caleb Ju*, Yifan Zhang*, Edgar Solomonik
  Foundations of Computational Mathematics
• [SIAM] [arXiv] [code]

  Derivation and analysis of fast bilinear algorithms for convolution

  
  Caleb Ju and Edgar Solomonik
  SIAM Review

*Equal contribution

(α) Alphabetical order