PolyFormer: learning efficient reformulations for scalable optimization under complex physical constraints

• URL: http://arxiv.org/abs/2603.08283v1
• Date: Mon, 09 Mar 2026 11:59:39 GMT
• Title: PolyFormer: learning efficient reformulations for scalable optimization under complex physical constraints
• Abstract summary: PolyFormer captures geometric structures behind constraints and transforms them into efficient polytopic reformulations.<n>It achieves computational speedups up to 6,400-fold and memory reductions up to 99.87%, while maintaining solution quality competitive with or superior to state-of-the-art methods.
• Score: 36.764168660407215
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Real-world optimization problems are often constrained by complex physical laws that limit computational scalability. These constraints are inherently tied to complex regions, and thus learning models that incorporate physical and geometric knowledge, i.e., physics-informed machine learning (PIML), offer a promising pathway for efficient solution. Here, we introduce PolyFormer, which opens a new direction for PIML in prescriptive optimization tasks, where physical and geometric knowledge is not merely used to regularize learning models, but to simplify the problems themselves. PolyFormer captures geometric structures behind constraints and transforms them into efficient polytopic reformulations, thereby decoupling problem complexity from solution difficulty and enabling off-the-shelf optimization solvers to efficiently produce feasible solutions with acceptable optimality loss. Through evaluations across three important problems (large-scale resource aggregation, network-constrained optimization, and optimization under uncertainty), PolyFormer achieves computational speedups up to 6,400-fold and memory reductions up to 99.87%, while maintaining solution quality competitive with or superior to state-of-the-art methods. These results demonstrate that PolyFormer provides an efficient and reliable solution for scalable constrained optimization, expanding the scope of PIML to prescriptive tasks in scientific discovery and engineering applications.

Related papers

• Efficient QAOA Architecture for Solving Multi-Constrained Optimization Problems [3.757262277494307]
  This paper proposes a novel combination of constraint encoding methods for the Quantum Approximate Optimization Ansatz.<n>One-hot constraints are enforced through $XY$-mixers that restrict the search space to the feasible sub-space naturally.<n>Since $XY$-mixers restrict the search space, specific state vector entries are always zero and can be omitted from the simulation, saving valuable memory and computing resources.
  arXiv  Detail & Related papers  (2025-06-03T17:46:53Z)
• Diverse Topology Optimization using Modulated Neural Fields [11.585099298173285]
  Topology optimization (TO) is a family of computational methods that derive near-optimal geometries from formal problem descriptions.<n>We introduce Modulated Neural Fields (TOM) - a data-free method that trains a neural network to generate structurally compliant shapes.<n>TOM generates more diverse solutions than any previous method, all while maintaining near-optimality and without relying on a dataset.
  arXiv  Detail & Related papers  (2025-02-17T21:24:18Z)
• Large Language Models for Combinatorial Optimization of Design Structure Matrix [4.513609458468522]
  Combinatorial optimization (CO) is essential for improving efficiency and performance in engineering applications. When it comes to real-world engineering problems, algorithms based on pure mathematical reasoning are limited and incapable to capture the contextual nuances necessary for optimization. This study explores the potential of Large Language Models (LLMs) in solving engineering CO problems by leveraging their reasoning power and contextual knowledge.
  arXiv  Detail & Related papers  (2024-11-19T15:39:51Z)
• OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling [62.19438812624467]
  Large language models (LLMs) have exhibited their problem-solving abilities in mathematical reasoning.<n>We propose OptiBench, a benchmark for End-to-end optimization problem-solving with human-readable inputs and outputs.
  arXiv  Detail & Related papers  (2024-07-13T13:27:57Z)
• Faster Stochastic Variance Reduction Methods for Compositional MiniMax Optimization [50.10952609321302]
  compositional minimax optimization is a pivotal challenge across various machine learning domains. Current methods of compositional minimax optimization are plagued by sub-optimal complexities or heavy reliance on sizable batch sizes. This paper introduces a novel method, called Nested STOchastic Recursive Momentum (NSTORM), which can achieve the optimal sample complexity of $O(kappa3 /epsilon3 )$.
  arXiv  Detail & Related papers  (2023-08-18T14:57:21Z)
• Learning Adaptive Evolutionary Computation for Solving Multi-Objective Optimization Problems [3.3266268089678257]
  This paper proposes a framework that integrates MOEAs with adaptive parameter control using Deep Reinforcement Learning (DRL) The DRL policy is trained to adaptively set the values that dictate the intensity and probability of mutation for solutions during optimization. We show the learned policy is transferable, i.e., the policy trained on a simple benchmark problem can be directly applied to solve the complex warehouse optimization problem.
  arXiv  Detail & Related papers  (2022-11-01T22:08:34Z)
• Sparse Polynomial Optimization: Theory and Practice [5.27013884159732]
  Book presents several efforts to tackle this challenge with important scientific implications. It provides alternative optimization schemes that scale well in terms of computational complexity. We present sparsity-exploiting hierarchies of relaxations, for either unconstrained or constrained problems.
  arXiv  Detail & Related papers  (2022-08-23T18:56:05Z)
• Speeding up Computational Morphogenesis with Online Neural Synthetic Gradients [51.42959998304931]
  A wide range of modern science and engineering applications are formulated as optimization problems with a system of partial differential equations (PDEs) as constraints. These PDE-constrained optimization problems are typically solved in a standard discretize-then-optimize approach. We propose a general framework to speed up PDE-constrained optimization using online neural synthetic gradients (ONSG) with a novel two-scale optimization scheme.
  arXiv  Detail & Related papers  (2021-04-25T22:43:51Z)
• Reinforcement Learning for Adaptive Mesh Refinement [63.7867809197671]
  We propose a novel formulation of AMR as a Markov decision process and apply deep reinforcement learning to train refinement policies directly from simulation. The model sizes of these policy architectures are independent of the mesh size and hence scale to arbitrarily large and complex simulations.
  arXiv  Detail & Related papers  (2021-03-01T22:55:48Z)
• Optimizing Wireless Systems Using Unsupervised and Reinforced-Unsupervised Deep Learning [96.01176486957226]
  Resource allocation and transceivers in wireless networks are usually designed by solving optimization problems. In this article, we introduce unsupervised and reinforced-unsupervised learning frameworks for solving both variable and functional optimization problems.
  arXiv  Detail & Related papers  (2020-01-03T11:01:52Z)

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.