Deep-Unfolded Coordination

• URL: http://arxiv.org/abs/2606.19920v1
• Date: Thu, 18 Jun 2026 08:14:43 GMT
• Title: Deep-Unfolded Coordination
• Abstract summary: Deep Coordinator is a deepunfolding framework that dynamically adjust tunings of ADMM-DDP.<n>Deep Coordinator produces comparable quality 6.18-9.44x than conventional solvers.
• Score: 14.215090107491754
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Distributed optimization is a highly scalable and structurally transparent technique to solve multi-agent robotics problems; however, such methods often suffer from the need for highly-specialized, problem-specific hyperparameter tunings. In this work, we propose Deep Coordinator, a deep-unfolding framework that learns to dynamically adjust the hyperparameters of ADMM-DDP, a popular distributed solver for robotics tasks, at solve-time in response to optimizer performance. Our architecture consists of unrolling a fixed number of ADMM-DDP iterations into a neural network with learnable functions between layers mapping the optimizer state to the next hyperparameters. To the best of our knowledge, Deep Coordinator is the first deep-unfolding framework to adapt the penalty parameters of a non-convex optimizer at solve-time; we show that the mainstream supervised approach can yield degenerate solutions when training such models, and propose an unsupervised learning scheme. On simulations with fleets of cars and quadrotors, Deep Coordinator produces trajectories of comparable quality 6.18-9.44x faster than conventional solvers. Furthermore, Deep Coordinator retains its performance benefits when deployed to systems up to 8x larger than trained on.

Related papers

• S$^3$LDBO: A Snapshot Single-Loop Algorithm for Decentralized Bilevel Optimization [19.171046927785333]
  Snapshot-SLDBO is an efficient single-loop decentralized bilevel optimization algorithm.<n>We show that Snapshot-SLDBO improves computational efficiency while maintaining competitive learning performance.
  arXiv  Detail & Related papers  (2026-05-29T13:44:46Z)
• An End-to-End Deep Reinforcement Learning Approach for Solving the Traveling Salesman Problem with Drones [12.385878815004283]
  This study proposes a hierarchical Actor-Critic deep reinforcement learning framework for solving the Traveling Salesman Problem with Drones (TSP-D)<n>The architecture consists of two primary computation: a Transformer-inspired encoder and an efficient Minimal Gated Unit decoder.<n>The entire framework operates within an asynchronous advantage actor-critic paradigm.
  arXiv  Detail & Related papers  (2025-11-07T14:26:29Z)
• A Unified Model for Multi-Task Drone Routing in Post-Disaster Road Assessment [14.07560120879767]
  Post-disaster road assessment (PDRA) is essential for emergency response, enabling rapid evaluation of infrastructure conditions.<n>Drones provide a flexible and effective tool for PDRA, routing them in large-scale networks remains challenging.<n>This study proposes a unified model (UM) for drone routing that simultaneously addresses eight PDRA variants.
  arXiv  Detail & Related papers  (2025-10-24T14:48:57Z)
• Learning to Coordinate: Distributed Meta-Trajectory Optimization Via Differentiable ADMM-DDP [4.880846795915428]
  We propose Learning to Coordinate (L2C) to adapt across diverse tasks and agent configurations.<n>L2C differentiates end-to-end through the ADMM-DDP pipeline in a distributed manner.<n>It achieves up to $88%$ faster gradient computation than state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-09-01T17:17:05Z)
• Learning to Solve the Min-Max Mixed-Shelves Picker-Routing Problem via Hierarchical and Parallel Decoding [0.3867363075280544]
  The Mixed-Shelves Picker Routing Problem (MSPRP) is a fundamental challenge in logistics, where pickers must navigate a mixed-shelves environment to retrieve SKUs efficiently.<n>We propose a novel hierarchical and parallel decoding approach for solving the min-max variant of the MSPRP via multi-agent reinforcement learning.<n> Experiments show state-of-the-art performance in both solution quality and inference speed, particularly for large-scale and out-of-distribution instances.
  arXiv  Detail & Related papers  (2025-02-14T15:42:30Z)
• FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression [55.992528247880685]
  Decentralized training faces significant challenges regarding system design and efficiency. We present FusionLLM, a decentralized training system designed and implemented for training large deep neural networks (DNNs) We show that our system and method can achieve 1.45 - 9.39x speedup compared to baseline methods while ensuring convergence.
  arXiv  Detail & Related papers  (2024-10-16T16:13:19Z)
• An Efficient Learning-based Solver Comparable to Metaheuristics for the Capacitated Arc Routing Problem [67.92544792239086]
  We introduce an NN-based solver to significantly narrow the gap with advanced metaheuristics. First, we propose direction-aware facilitating attention model (DaAM) to incorporate directionality into the embedding process. Second, we design a supervised reinforcement learning scheme that involves supervised pre-training to establish a robust initial policy.
  arXiv  Detail & Related papers  (2024-03-11T02:17:42Z)
• A Multi-Head Ensemble Multi-Task Learning Approach for Dynamical Computation Offloading [62.34538208323411]
  We propose a multi-head ensemble multi-task learning (MEMTL) approach with a shared backbone and multiple prediction heads (PHs) MEMTL outperforms benchmark methods in both the inference accuracy and mean square error without requiring additional training data.
  arXiv  Detail & Related papers  (2023-09-02T11:01:16Z)
• Collaborative Intelligent Reflecting Surface Networks with Multi-Agent Reinforcement Learning [63.83425382922157]
  Intelligent reflecting surface (IRS) is envisioned to be widely applied in future wireless networks. In this paper, we investigate a multi-user communication system assisted by cooperative IRS devices with the capability of energy harvesting.
  arXiv  Detail & Related papers  (2022-03-26T20:37:14Z)
• Phase Retrieval using Expectation Consistent Signal Recovery Algorithm based on Hypernetwork [73.94896986868146]
  Phase retrieval is an important component in modern computational imaging systems. Recent advances in deep learning have opened up a new possibility for robust and fast PR. We develop a novel framework for deep unfolding to overcome the existing limitations.
  arXiv  Detail & Related papers  (2021-01-12T08:36:23Z)
• Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks [50.42141893913188]
  We study a distributed variable for large-scale AUC for a neural network as with a deep neural network. Our model requires a much less number of communication rounds and still a number of communication rounds in theory. Our experiments on several datasets show the effectiveness of our theory and also confirm our theory.
  arXiv  Detail & Related papers  (2020-05-05T18:08:23Z)

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.