DIM: Enforcing Domain-Informed Monotonicity in Deep Neural Networks

• URL: http://arxiv.org/abs/2509.21666v1
• Date: Thu, 25 Sep 2025 22:35:57 GMT
• Title: DIM: Enforcing Domain-Informed Monotonicity in Deep Neural Networks
• Authors: Joshua Salim, Jordan Yu, Xilei Zhao,
• Abstract summary: This paper proposes a new regularization method, i.e., Enforcing Domain-Informed Monotonicity in Deep Neural Networks (DIM)<n>DIM maintains domain-informed monotonic relationships in complex deep learning models to further improve predictions.<n>We test and validate the proposed methodology using a real-world ridesourcing dataset from Chicago and a synthetically created dataset.
• Score: 2.599882743586164
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While deep learning models excel at predictive tasks, they often overfit due to their complex structure and large number of parameters, causing them to memorize training data, including noise, rather than learn patterns that generalize to new data. To tackle this challenge, this paper proposes a new regularization method, i.e., Enforcing Domain-Informed Monotonicity in Deep Neural Networks (DIM), which maintains domain-informed monotonic relationships in complex deep learning models to further improve predictions. Specifically, our method enforces monotonicity by penalizing violations relative to a linear baseline, effectively encouraging the model to follow expected trends while preserving its predictive power. We formalize this approach through a comprehensive mathematical framework that establishes a linear reference, measures deviations from monotonic behavior, and integrates these measurements into the training objective. We test and validate the proposed methodology using a real-world ridesourcing dataset from Chicago and a synthetically created dataset. Experiments across various neural network architectures show that even modest monotonicity constraints consistently enhance model performance. DIM enhances the predictive performance of deep neural networks by applying domain-informed monotonicity constraints to regularize model behavior and mitigate overfitting

Related papers

• Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction [55.914891182214475]
  We introduce neural network reprogrammability as a unifying framework for model adaptation.<n>We present a taxonomy that categorizes such information manipulation approaches across four key dimensions.<n>We also analyze remaining technical challenges and ethical considerations.
  arXiv  Detail & Related papers  (2025-06-05T05:42:27Z)
• Monotone Peridynamic Neural Operator for Nonlinear Material Modeling with Conditionally Unique Solutions [8.178003326156418]
  We introduce monotone peridynamic neural operator (MPNO), a novel data-driven nonlocal model learning approach based on neural operators.<n>MPNO learns a nonlocal kernel together with a nonlinear relation, while ensuring solution uniqueness through a monotone gradient network.<n>We show that MPNO exhibits superior generalization capabilities than the conventional neural networks.
  arXiv  Detail & Related papers  (2025-05-02T07:10:31Z)
• Generalized Factor Neural Network Model for High-dimensional Regression [50.554377879576066]
  We tackle the challenges of modeling high-dimensional data sets with latent low-dimensional structures hidden within complex, non-linear, and noisy relationships.<n>Our approach enables a seamless integration of concepts from non-parametric regression, factor models, and neural networks for high-dimensional regression.
  arXiv  Detail & Related papers  (2025-02-16T23:13:55Z)
• Regularized Neural Ensemblers [55.15643209328513]
  In this study, we explore employing regularized neural networks as ensemble methods.<n>Motivated by the risk of learning low-diversity ensembles, we propose regularizing the ensembling model by randomly dropping base model predictions.<n>We demonstrate this approach provides lower bounds for the diversity within the ensemble, reducing overfitting and improving generalization capabilities.
  arXiv  Detail & Related papers  (2024-10-06T15:25:39Z)
• Nonlinear denoising score matching for enhanced learning of structured distributions [12.428200977408817]
  Generalizing to a nonlinear drift allows for additional structure to be incorporated into the dynamics.<n>Our method learns score-based generative models with less data by flexibly incorporating structure arising in the dataset.
  arXiv  Detail & Related papers  (2024-05-24T15:14:23Z)
• The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning [31.8260779160424]
  We investigate how popular algorithms perform as the learned dynamics model is improved.<n>We propose Reach-Aware Learning (RAVL), a simple and robust method that directly addresses the edge-of-reach problem.
  arXiv  Detail & Related papers  (2024-02-19T20:38:00Z)
• Towards Theoretical Understandings of Self-Consuming Generative Models [56.84592466204185]
  This paper tackles the emerging challenge of training generative models within a self-consuming loop. We construct a theoretical framework to rigorously evaluate how this training procedure impacts the data distributions learned by future models. We present results for kernel density estimation, delivering nuanced insights such as the impact of mixed data training on error propagation.
  arXiv  Detail & Related papers  (2024-02-19T02:08:09Z)
• A PAC-Bayesian Perspective on the Interpolating Information Criterion [54.548058449535155]
  We show how a PAC-Bayes bound is obtained for a general class of models, characterizing factors which influence performance in the interpolating regime. We quantify how the test error for overparameterized models achieving effectively zero training error depends on the quality of the implicit regularization imposed by e.g. the combination of model, parameter-initialization scheme.
  arXiv  Detail & Related papers  (2023-11-13T01:48:08Z)
• On the Generalization and Adaption Performance of Causal Models [99.64022680811281]
  Differentiable causal discovery has proposed to factorize the data generating process into a set of modules. We study the generalization and adaption performance of such modular neural causal models. Our analysis shows that the modular neural causal models outperform other models on both zero and few-shot adaptation in low data regimes.
  arXiv  Detail & Related papers  (2022-06-09T17:12:32Z)
• Certified Monotonic Neural Networks [15.537695725617576]
  We propose to certify the monotonicity of the general piece-wise linear neural networks by solving a mixed integer linear programming problem. Our approach does not require human-designed constraints on the weight space and also yields more accurate approximation.
  arXiv  Detail & Related papers  (2020-11-20T04:58:13Z)
• Sparsely constrained neural networks for model discovery of PDEs [0.0]
  We present a modular framework that determines the sparsity pattern of a deep-learning based surrogate using any sparse regression technique. We show how a different network architecture and sparsity estimator improve model discovery accuracy and convergence on several benchmark examples.
  arXiv  Detail & Related papers  (2020-11-09T11:02:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.