Enforcing Hard Linear Constraints in Deep Learning Models with Decision Rules

• URL: http://arxiv.org/abs/2505.13858v1
• Date: Tue, 20 May 2025 03:09:44 GMT
• Title: Enforcing Hard Linear Constraints in Deep Learning Models with Decision Rules
• Authors: Gonzalo E. Constante-Flores, Hao Chen, Can Li,
• Abstract summary: This paper proposes a model-agnostic framework for enforcing input-dependent linear equality and inequality constraints on neural network outputs.<n>The architecture combines a task network trained for prediction accuracy with a safe network trained using decision rules from the runtime and robust optimization to ensure feasibility across the entire input space.
• Score: 8.098452803458253
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning models are increasingly deployed in safety-critical tasks where predictions must satisfy hard constraints, such as physical laws, fairness requirements, or safety limits. However, standard architectures lack built-in mechanisms to enforce such constraints, and existing approaches based on regularization or projection are often limited to simple constraints, computationally expensive, or lack feasibility guarantees. This paper proposes a model-agnostic framework for enforcing input-dependent linear equality and inequality constraints on neural network outputs. The architecture combines a task network trained for prediction accuracy with a safe network trained using decision rules from the stochastic and robust optimization literature to ensure feasibility across the entire input space. The final prediction is a convex combination of the two subnetworks, guaranteeing constraint satisfaction during both training and inference without iterative procedures or runtime optimization. We prove that the architecture is a universal approximator of constrained functions and derive computationally tractable formulations based on linear decision rules. Empirical results on benchmark regression tasks show that our method consistently satisfies constraints while maintaining competitive accuracy and low inference latency.

Related papers

• End-to-End Probabilistic Framework for Learning with Hard Constraints [47.10876360975842]
  ProbHardE2E learns systems that can incorporate operational/physical constraints as hard requirements.<n>It enforces hard constraints by exploiting variance information in a novel way.<n>It can incorporate a range of non-linear constraints (increasing the power of modeling and flexibility)
  arXiv  Detail & Related papers  (2025-06-08T05:29:50Z)
• Conformal Mixed-Integer Constraint Learning with Feasibility Guarantees [0.3058340744328236]
  Conformal Mixed-Integer Constraint Learning provides probabilistic feasibility guarantees for data-driven constraints in optimization problems.<n>We show that C-MICL consistently achieves target rates, maintains competitive objective performance, and significantly reduces computational cost compared to existing methods.
  arXiv  Detail & Related papers  (2025-06-04T03:26:31Z)
• Constrained Online Decision-Making: A Unified Framework [14.465944215100746]
  We investigate a general formulation of sequential decision-making with stage-wise feasibility constraints.<n>We propose a unified algorithmic framework that captures many existing constrained learning problems.<n>Our result offers a principled foundation for constrained sequential decision-making in both theory and practice.
  arXiv  Detail & Related papers  (2025-05-11T19:22:04Z)
• ENFORCE: Nonlinear Constrained Learning with Adaptive-depth Neural Projection [0.0]
  We introduce ENFORCE, a neural network architecture that uses an adaptive projection module (AdaNP) to enforce nonlinear equality constraints in the predictions.<n>We prove that our projection mapping is 1-Lipschitz, making it well-suited for stable training.<n>The predictions of our new architecture satisfy $N_C$ equality constraints that are nonlinear in both the inputs and outputs of the neural network.
  arXiv  Detail & Related papers  (2025-02-10T18:52:22Z)
• Hard-Constrained Neural Networks with Universal Approximation Guarantees [6.03124479597323]
  HardNet is a framework for constructing neural networks that inherently satisfy hard constraints without sacrificing model capacity.<n>We show that HardNet retains the universal approximation capabilities of neural networks.<n>We demonstrate HardNet across various applications: learning with piecewise constraints, learning optimization solvers, optimizing control policies in safety-critical systems, and learning safe decision logic for aircraft systems.
  arXiv  Detail & Related papers  (2024-10-14T17:59:24Z)
• Robust Stochastically-Descending Unrolled Networks [85.6993263983062]
  Deep unrolling is an emerging learning-to-optimize method that unrolls a truncated iterative algorithm in the layers of a trainable neural network.<n>We show that convergence guarantees and generalizability of the unrolled networks are still open theoretical problems.<n>We numerically assess unrolled architectures trained under the proposed constraints in two different applications.
  arXiv  Detail & Related papers  (2023-12-25T18:51:23Z)
• On Regularization and Inference with Label Constraints [62.60903248392479]
  We compare two strategies for encoding label constraints in a machine learning pipeline, regularization with constraints and constrained inference. For regularization, we show that it narrows the generalization gap by precluding models that are inconsistent with the constraints. For constrained inference, we show that it reduces the population risk by correcting a model's violation, and hence turns the violation into an advantage.
  arXiv  Detail & Related papers  (2023-07-08T03:39:22Z)
• Neural Fields with Hard Constraints of Arbitrary Differential Order [61.49418682745144]
  We develop a series of approaches for enforcing hard constraints on neural fields. The constraints can be specified as a linear operator applied to the neural field and its derivatives. Our approaches are demonstrated in a wide range of real-world applications.
  arXiv  Detail & Related papers  (2023-06-15T08:33:52Z)
• Resilient Constrained Learning [94.27081585149836]
  This paper presents a constrained learning approach that adapts the requirements while simultaneously solving the learning task. We call this approach resilient constrained learning after the term used to describe ecological systems that adapt to disruptions by modifying their operation.
  arXiv  Detail & Related papers  (2023-06-04T18:14:18Z)
• When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning [62.00672284480755]
  This paper aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent. Accurate models of expertise in executing a task has applications in safety-sensitive applications such as clinical decision making and autonomous driving.
  arXiv  Detail & Related papers  (2023-02-15T04:14:20Z)
• Constrained Model-Free Reinforcement Learning for Process Optimization [0.0]
  Reinforcement learning (RL) is a control approach that can handle nonlinear optimal control problems. Despite the promise exhibited, RL has yet to see marked translation to industrial practice. We propose an 'oracle'-assisted constrained Q-learning algorithm that guarantees the satisfaction of joint chance constraints with a high probability.
  arXiv  Detail & Related papers  (2020-11-16T13:16:22Z)
• An Integer Linear Programming Framework for Mining Constraints from Data [81.60135973848125]
  We present a general framework for mining constraints from data. In particular, we consider the inference in structured output prediction as an integer linear programming (ILP) problem. We show that our approach can learn to solve 9x9 Sudoku puzzles and minimal spanning tree problems from examples without providing the underlying rules.
  arXiv  Detail & Related papers  (2020-06-18T20:09:53Z)

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.