Jiatai Tong

Optimization over Trained (and Sparse) Neural Networks: A Surrogate within a Surrogate

  • Hung Pham
  • Zhiyi Ren
  • Jiatai Tong
  • Thiago Serra
    • Categories (Mixed) Integer Linear Programming, Integer Programming

    We can approximate a constraint or an objective function that is uncertain or nonlinear with a neural network that we embed in the optimization model. This approach, which is known as constraint learning, faces the challenge that optimization models with neural network surrogates are harder to solve. Such difficulties have motivated studies on model reformulation, … Read more

    Optimization Over Trained Neural Networks: Taking a Relaxing Walk

  • Jiatai Tong
  • Junyang Cai
  • Thiago Serra
    • Categories (Mixed) Integer Linear Programming, Data-Mining, Meta Heuristics

    Besides training, mathematical optimization is also used in deep learning to model and solve formulations over trained neural networks for purposes such as verification, compression, and optimization with learned constraints. However, solving these formulations soon becomes difficult as the network size grows due to the weak linear relaxation and dense constraint matrix. We have seen … Read more