Constrained Flow Matching via Lagrangian Dual Flows

• URL: http://arxiv.org/abs/2607.04513v1
• Date: Sun, 05 Jul 2026 21:25:51 GMT
• Title: Constrained Flow Matching via Lagrangian Dual Flows
• Abstract summary: We introduce Lagrangian Dual Flows, a new family of constrained generation techniques based on Lagrangian dual dynamics.<n>By simply flowing a dual co-state alongside generated samples, we can guarantee nonlinear constraint satisfaction without expensive optimization subproblems.<n>The resulting constrained generation algorithms are simple, effective, and open new theoretical connections between flow matching and primal-dual methods in numerical optimization.
• Score: 47.76010089014289
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Flow matching is a powerful tool for generative modeling, but emerging applications in robotics, planning, and physics require inference-time constraints on generated outputs. Such constraints are often complex and highly nonlinear. As a result, methods designed for linear constraints like image inpainting are rarely sufficient, and projection or optimization-based alternatives can be prohibitively expensive. In this paper, we introduce Lagrangian Dual Flows, a new family of constrained generation techniques based on Lagrangian dual dynamics. By simply flowing a dual co-state alongside generated samples, we can guarantee nonlinear constraint satisfaction without expensive optimization subproblems, pseudoinverses, or projection steps during the denoising process. The resulting constrained generation algorithms are simple, effective, and open new theoretical connections between flow matching and primal-dual methods in numerical optimization.

Related papers

• SNAP-FM: Sparse Nonlinear Accelerated Projection for Physics-Constrained Generative Modeling [3.2297343473068882]
  Constrained sampling closes this gap, enforcing constraints exactly at inference time without retraining.<n>Standard ML frameworks obscure the structure that physical constraints induce naturally.<n>We exploit this bottleneck by exploiting the structure that sample-wise and local PDE couplings induce in the projection subproblems.
  arXiv  Detail & Related papers  (2026-06-30T19:35:09Z)
• Learning Constrained Optimization with Deep Augmented Lagrangian Methods [54.22290715244502]
  A machine learning (ML) model is trained to emulate a constrained optimization solver. This paper proposes an alternative approach, in which the ML model is trained to predict dual solution estimates directly. It enables an end-to-end training scheme is which the dual objective is as a loss function, and solution estimates toward primal feasibility, emulating a Dual Ascent method.
  arXiv  Detail & Related papers  (2024-03-06T04:43:22Z)
• Dual Lagrangian Learning for Conic Optimization [18.006916033168494]
  The paper introduces a systematic dual completion procedure, differentiable conic projection layers, and a self-supervised learning framework based on Lagrangian duality. It also provides closed-form dual completion formulae for broad classes of conic problems, which eliminate the need for costly implicit layers. The proposed methodology significantly outperforms a state-of-the-art learning-based method, and achieves 1000x speedups over commercial interior-point solvers with optimality gaps under 0.5% on average.
  arXiv  Detail & Related papers  (2024-02-05T15:14:08Z)
• Learning Lagrangian Multipliers for the Travelling Salesman Problem [12.968608204035611]
  We propose an innovative unsupervised learning approach that harnesses the capabilities of graph neural networks to exploit the problem structure. We apply this technique to the well-known Held-Karp Lagrangian relaxation for the travelling salesman problem. In contrast to much of the existing literature, which primarily focuses on finding feasible solutions, our approach operates on the dual side, demonstrating that learning can also accelerate the proof of optimality.
  arXiv  Detail & Related papers  (2023-12-22T17:09:34Z)
• Accelerated First-Order Optimization under Nonlinear Constraints [61.98523595657983]
  We exploit between first-order algorithms for constrained optimization and non-smooth systems to design a new class of accelerated first-order algorithms.<n>An important property of these algorithms is that constraints are expressed in terms of velocities instead of sparse variables.
  arXiv  Detail & Related papers  (2023-02-01T08:50:48Z)
• Symmetric Tensor Networks for Generative Modeling and Constrained Combinatorial Optimization [72.41480594026815]
  Constrained optimization problems abound in industry, from portfolio optimization to logistics. One of the major roadblocks in solving these problems is the presence of non-trivial hard constraints which limit the valid search space. In this work, we encode arbitrary integer-valued equality constraints of the form Ax=b, directly into U(1) symmetric networks (TNs) and leverage their applicability as quantum-inspired generative models.
  arXiv  Detail & Related papers  (2022-11-16T18:59:54Z)
• On Constraints in First-Order Optimization: A View from Non-Smooth Dynamical Systems [99.59934203759754]
  We introduce a class of first-order methods for smooth constrained optimization. Two distinctive features of our approach are that projections or optimizations over the entire feasible set are avoided. The resulting algorithmic procedure is simple to implement even when constraints are nonlinear.
  arXiv  Detail & Related papers  (2021-07-17T11:45:13Z)
• A Stochastic Composite Augmented Lagrangian Method For Reinforcement Learning [9.204659134755795]
  We consider the linear programming (LP) formulation for deep reinforcement learning. The augmented Lagrangian method suffers the double-sampling obstacle in solving the LP. A deep parameterized augment Lagrangian method is proposed.
  arXiv  Detail & Related papers  (2021-05-20T13:08:06Z)
• Scaling the Convex Barrier with Sparse Dual Algorithms [141.4085318878354]
  We present two novel dual algorithms for tight and efficient neural network bounding. Both methods recover the strengths of the new relaxation: tightness and a linear separation oracle. We can obtain better bounds than off-the-shelf solvers in only a fraction of their running time.
  arXiv  Detail & Related papers  (2021-01-14T19:45:17Z)

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.