Smooth Min-Max Monotonic Networks
About
Monotonicity constraints are powerful regularizers in statistical modelling. They can support fairness in computer-aided decision making and increase plausibility in data-driven scientific models. The seminal min-max (MM) neural network architecture ensures monotonicity, but often gets stuck in undesired local optima during training because of partial derivatives of the MM nonlinearities being zero. We propose a simple modification of the MM network using strictly-increasing smooth minimum and maximum functions that alleviates this problem. The resulting smooth min-max (SMM) network module inherits the asymptotic approximation properties from the MM architecture. It can be used within larger deep learning systems trained end-to-end. The SMM module is conceptually simple and computationally less demanding than state-of-the-art neural networks for monotonic modelling. Our experiments show that this does not come with a loss in generalization performance compared to alternative neural and non-neural approaches.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Classification | COMPAS (test) | Accuracy69.5 | 16 | |
| Regression | BlogFeedback SMM ICML-2024 regression benchmark suite (test) | RMSE0.154 | 10 | |
| Classification | LoanDefaulter (test) | Test Accuracy65.47 | 10 | |
| Classification | Heart Disease (test) | Test Accuracy91.3 | 7 | |
| Regression | Auto MPG SMM ICML-2024 regression benchmark suite (test) | MSE7.51 | 6 | |
| Disentangled Representation Learning | synthetic ellipses dataset | Reconstruction L2 Norm37 | 5 | |
| Classification | ChestXray (test) | Accuracy (Pretrained)67.9 | 4 | |
| Monotone multivariate function approximation | SMM Monotone multivariate function approximation (Nin=2) ICML-2024 (test) | Median MSE0.00e+0 | 4 | |
| Monotone multivariate function approximation | SMM (Nin=6) ICML-2024 (test) | Median MSE0.02 | 4 | |
| Monotone multivariate function approximation | SMM Monotone multivariate function approximation (Nin=4) (test) | Median MSE0.01 | 4 |