mPOLICE: Provable Enforcement of Multi-Region Affine Constraints in Deep Neural Networks

• URL: http://arxiv.org/abs/2502.02434v2
• Date: Mon, 26 May 2025 16:16:03 GMT
• Title: mPOLICE: Provable Enforcement of Multi-Region Affine Constraints in Deep Neural Networks
• Authors: Mohammadmehdi Ataei, Hyunmin Cheong, Adrian Butscher,
• Abstract summary: mPOLICE is a new approach that generalizes POLICE to provably enforce affine constraints over multiple disjoint convex regions.<n>We introduce a training algorithm that incorporates mPOLICE into conventional deep learning pipelines.<n>We validate the flexibility and effectiveness of mPOLICE through experiments across various applications.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep neural networks are increasingly used in safety-critical domains such as robotics and scientific modeling, where strict adherence to output constraints is essential. Methods like POLICE, which are tailored for single convex regions, face challenges when extended to multiple disjoint regions, often leading to constraint violations or unwanted affine behavior across regions. This paper proposes mPOLICE, a new approach that generalizes POLICE to provably enforce affine constraints over multiple disjoint convex regions. At its core, mPOLICE assigns distinct neuron activation patterns to each constrained region, enabling localized affine behavior and avoiding unintended generalization. This is implemented through a layer-wise optimization of the network parameters. Additionally, we introduce a training algorithm that incorporates mPOLICE into conventional deep learning pipelines, balancing task-specific performance with constraint enforcement using periodic sign pattern enforcement. We validate the flexibility and effectiveness of mPOLICE through experiments across various applications, including safety-critical reinforcement learning, implicit 3D shape representation with geometric constraints, and fluid dynamics simulations with boundary condition enforcement. Importantly, mPOLICE incurs no runtime overhead during inference, making it a practical and reliable solution for constraint handling in deep neural networks.

Related papers

• Reinforcement learning with combinatorial actions for coupled restless bandits [62.89013331120493]
  We propose SEQUOIA, an RL algorithm that directly optimize for long-term reward over the feasible action space. We empirically validate SEQUOIA on four novel restless bandit problems with constraints: multiple interventions, path constraints, bipartite matching, and capacity constraints.
  arXiv  Detail & Related papers  (2025-03-01T21:25:21Z)
• Diffusion Predictive Control with Constraints [51.91057765703533]
  Diffusion predictive control with constraints (DPCC)<n>An algorithm for diffusion-based control with explicit state and action constraints that can deviate from those in the training data.<n>We show through simulations of a robot manipulator that DPCC outperforms existing methods in satisfying novel test-time constraints while maintaining performance on the learned control task.
  arXiv  Detail & Related papers  (2024-12-12T15:10:22Z)
• Learning to Explore with Lagrangians for Bandits under Unknown Linear Constraints [8.784438985280094]
  We study problems as pure exploration in multi-armed bandits with unknown linear constraints. First, we propose a Lagrangian relaxation of the sample complexity lower bound for pure exploration under constraints. Second, we leverage the Lagrangian lower bound and the properties of convex to propose two computationally efficient extensions of Track-and-Stop and Gamified Explorer, namely LATS and LAGEX.
  arXiv  Detail & Related papers  (2024-10-24T15:26:14Z)
• Verifying message-passing neural networks via topology-based bounds tightening [3.3267518043390205]
  We develop a computationally effective approach towards providing robust certificates for message-passing neural networks (MPNNs) Because our work builds on mixed-integer optimization, it encodes a wide variety of subproblems. We test on both node and graph classification problems and consider topological attacks that both add and remove edges.
  arXiv  Detail & Related papers  (2024-02-21T17:05:27Z)
• 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)
• 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)
• Constrained Empirical Risk Minimization: Theory and Practice [2.4934936799100034]
  We present a framework that allows the exact enforcement of constraints on parameterized sets of functions such as Deep Neural Networks (DNNs) We focus on constraints that are outside the scope of equivariant networks used in Geometric Deep Learning. As a major example of the framework, we restrict filters of a Convolutional Neural Network (CNN) to be wavelets, and apply these wavelet networks to the task of contour prediction in the medical domain.
  arXiv  Detail & Related papers  (2023-02-09T16:11:58Z)
• DRIP: Domain Refinement Iteration with Polytopes for Backward Reachability Analysis of Neural Feedback Loops [12.706980346861986]
  This work investigates backward reachability as a framework for providing collision avoidance guarantees for systems controlled by neural network (NN) policies. Because NNs are typically not invertible, existing methods assume a domain over which to relax the NN, which causes loose over-approximations of the set of states. We introduce DRIP, an algorithm with a refinement loop on the relaxation domain, which substantially tightens the BP set bounds.
  arXiv  Detail & Related papers  (2022-12-09T03:06:58Z)
• Multilevel-in-Layer Training for Deep Neural Network Regression [1.6185544531149159]
  We present a multilevel regularization strategy that constructs and trains a hierarchy of neural networks. We experimentally show with PDE regression problems that our multilevel training approach is an effective regularizer.
  arXiv  Detail & Related papers  (2022-11-11T23:53:46Z)
• Multi-Objective Policy Gradients with Topological Constraints [108.10241442630289]
  We present a new algorithm for a policy gradient in TMDPs by a simple extension of the proximal policy optimization (PPO) algorithm. We demonstrate this on a real-world multiple-objective navigation problem with an arbitrary ordering of objectives both in simulation and on a real robot.
  arXiv  Detail & Related papers  (2022-09-15T07:22:58Z)
• Deep Policy Dynamic Programming for Vehicle Routing Problems [89.96386273895985]
  We propose Deep Policy Dynamic Programming (D PDP) to combine the strengths of learned neurals with those of dynamic programming algorithms. D PDP prioritizes and restricts the DP state space using a policy derived from a deep neural network, which is trained to predict edges from example solutions. We evaluate our framework on the travelling salesman problem (TSP) and the vehicle routing problem (VRP) and show that the neural policy improves the performance of (restricted) DP algorithms.
  arXiv  Detail & Related papers  (2021-02-23T15:33:57Z)
• Dealing with Non-Stationarity in Multi-Agent Reinforcement Learning via Trust Region Decomposition [52.06086375833474]
  Non-stationarity is one thorny issue in multi-agent reinforcement learning. We introduce a $delta$-stationarity measurement to explicitly model the stationarity of a policy sequence. We propose a trust region decomposition network based on message passing to estimate the joint policy divergence.
  arXiv  Detail & Related papers  (2021-02-21T14:46:50Z)
• Chance-Constrained Control with Lexicographic Deep Reinforcement Learning [77.34726150561087]
  This paper proposes a lexicographic Deep Reinforcement Learning (DeepRL)-based approach to chance-constrained Markov Decision Processes. A lexicographic version of the well-known DeepRL algorithm DQN is also proposed and validated via simulations.
  arXiv  Detail & Related papers  (2020-10-19T13:09:14Z)
• Deep Reinforcement Learning with Robust and Smooth Policy [90.78795857181727]
  We propose to learn a smooth policy that behaves smoothly with respect to states. We develop a new framework -- textbfSmooth textbfRegularized textbfReinforcement textbfLearning ($textbfSR2textbfL$), where the policy is trained with smoothness-inducing regularization. Such regularization effectively constrains the search space, and enforces smoothness in the learned policy.
  arXiv  Detail & Related papers  (2020-03-21T00:10:29Z)
• Local Propagation in Constraint-based Neural Network [77.37829055999238]
  We study a constraint-based representation of neural network architectures. We investigate a simple optimization procedure that is well suited to fulfil the so-called architectural constraints.
  arXiv  Detail & Related papers  (2020-02-18T16:47:38Z)
• Reinforcement Learning for POMDP: Partitioned Rollout and Policy Iteration with Application to Autonomous Sequential Repair Problems [2.6389022766562236]
  We consider infinite horizon discounted dynamic programming problems with finite state and control spaces, and partial state observations. We discuss an algorithm that uses multistep lookahead, truncated rollout with a known base policy, and a terminal cost function approximation.
  arXiv  Detail & Related papers  (2020-02-11T02:38:38Z)

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.