Homepage
Resume
Back to top
  • With New Deep Learning Models

Computational Economics (Discontinuous Neural Networks)

Economics assumes that agents are best responding. When best responses change, utilities may change discontinuously. Therefore, we develop discontinuous networks to deal with these problems.

Piecewise Linear, Discontinuous Network

Paper

Designed for contract design, where the utility function is piecewise linear but discontinuous. [NeurIPS 2023]

 

For the figure below: (a) The exact surface of the principal’s utility function. (b) A learned ReLU network cannot model the discontinuity of the function and yields an incorrect contract as shown in (a). (c) A learned DeLU network represents a discontinuous function and can well-approximate the ground-truth.

image

Piecewise Non-Linear, Discontinuous Network

Paper

Designed for multi-sender persuasion, where the utility function is piecewise non-linear and discontinuous. [ICML 2024]

 

In each column below, we show the ground-truth principal's utility and the approximation results achieved by our method, ReLU, and piecewise linear discontinuous networks, respectively.

image