Rethink Efficiency Side of Neural Combinatorial Solver: An Offline and Self-Play Paradigm

• URL: http://arxiv.org/abs/2602.20730v1
• Date: Tue, 24 Feb 2026 09:53:24 GMT
• Title: Rethink Efficiency Side of Neural Combinatorial Solver: An Offline and Self-Play Paradigm
• Abstract summary: We propose ECO, a versatile learning paradigm that enables efficient offline self-play for Neural Combinatorial Optimization (NCO)<n>Moving beyond inefficient online paradigms, we introduce a two-phase offline paradigm consisting of supervised warm-up and iterative Direct Preference Optimization (DPO)<n>To stabilize training, we employ a bootstrapping mechanism that ensures continuous policy improvement during training.
• Score: 20.747096255486838
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose ECO, a versatile learning paradigm that enables efficient offline self-play for Neural Combinatorial Optimization (NCO). ECO addresses key limitations in the field through: 1) Paradigm Shift: Moving beyond inefficient online paradigms, we introduce a two-phase offline paradigm consisting of supervised warm-up and iterative Direct Preference Optimization (DPO); 2) Architecture Shift: We deliberately design a Mamba-based architecture to further enhance the efficiency in the offline paradigm; and 3) Progressive Bootstrapping: To stabilize training, we employ a heuristic-based bootstrapping mechanism that ensures continuous policy improvement during training. Comparison results on TSP and CVRP highlight that ECO performs competitively with up-to-date baselines, with significant advantage on the efficiency side in terms of memory utilization and training throughput. We provide further in-depth analysis on the efficiency, throughput and memory usage of ECO. Ablation studies show rationale behind our designs.

Related papers

• Direct Advantage Estimation for Scalable and Sample-efficient Deep Reinforcement Learning [54.916555668983726]
  We introduce discrete latent dynamics models that efficiently approximate transition probabilities.<n>We find that DAE scales effectively with function approximator capacity while retaining high sample efficiency.
  arXiv  Detail & Related papers  (2026-06-18T15:58:48Z)
• EUPHORIA: Efficient Universal Planning via Hybrid Optimization for Robust Industrial Robotic Assembly [12.727917085274841]
  EUPHORIA is a unified framework that achieves universal few-shot adaptability and dynamic efficiency.<n>For structural reasoning, we introduce a Physics-Informed Graph Transformer trained via Soft Actor-Critic.<n>Experiments show that EUPHORIA significantly reduces energy consumption over decoupled baselines.
  arXiv  Detail & Related papers  (2026-05-15T18:25:49Z)
• Evolution of Optimization Methods: Algorithms, Scenarios, and Evaluations [98.44542103979735]
  First-order gradient descent methods, epitomized by gradient descent (SGD) and Adam, serve as the cornerstone of modern training pipelines.<n>Large-scale model training, stringent privacy requirements, and distributed learning paradigms expose critical limitations in these conventional approaches regarding privacy protection and memory efficiency.<n>We retrospectively analyze the evolutionary trajectory of deep learning optimization algorithms and present a comprehensive empirical evaluation of mainstreams across diverse model architectures and training scenarios.<n>We distill key emerging trends and fundamental design trade-offs, pinpointing promising directions for future research.
  arXiv  Detail & Related papers  (2026-04-14T17:01:36Z)
• NetworkFF: Unified Layer Optimization in Forward-Only Neural Networks [0.0]
  This paper introduces Collaborative Forward-Forward (CFF) learning, extending the original algorithm through inter-layer cooperation mechanisms.<n> Comprehensive evaluation on MNIST and Fashion-MNIST demonstrates significant performance improvements over baseline Forward-Forward implementations.<n>These findings establish inter-layer collaboration as a fundamental enhancement to Forward-Forward learning, with immediate applicability to neuromorphic computing architectures and energy-constrained AI systems.
  arXiv  Detail & Related papers  (2025-12-19T12:54:03Z)
• Efficient Reinforcement Learning from Human Feedback via Bayesian Preference Inference [0.29057513016551245]
  We propose a hybrid framework that unifies RLHF's scalability with PBO's query efficiency.<n>We validate the proposed approach on two representative domains: (i) high-dimensional preference optimization and (ii) LLM fine-tuning.
  arXiv  Detail & Related papers  (2025-11-06T11:27:38Z)
• More Than Memory Savings: Zeroth-Order Optimization Mitigates Forgetting in Continual Learning [10.698225972251839]
  Zeroth-order (ZO) optimization has gained attention as a memory-efficient alternative to first-order (FO) methods.<n>We show that ZO optimization naturally leads to flatter loss landscapes, which in turn reduce forgetting in continuous learning.<n>This stability comes at a cost of plasticity: due to its imprecise gradient estimates and slower convergence, ZO optimization tends to be less effective than FO in acquiring new task-specific knowledge.<n>We propose ZO-FC, a simple but effective approach that applies ZO optimization to a single adapter-based PEFT module with FO optimized classifier.
  arXiv  Detail & Related papers  (2025-10-23T21:54:00Z)
• SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous Driving [51.47621083057114]
  SOLVE is an innovative framework that synergizes Vision-Language Models with end-to-end (E2E) models to enhance autonomous vehicle planning.<n>Our approach emphasizes knowledge sharing at the feature level through a shared visual encoder, enabling comprehensive interaction between VLM and E2E components.
  arXiv  Detail & Related papers  (2025-05-22T15:44:30Z)
• Meta-Black-Box-Optimization through Offline Q-function Learning [17.565058993388707]
  We propose an offline learning-based MetaBBO framework, termed Q-Mamba, to attain both effectiveness and efficiency in MetaBBO.<n>Under this setting, we propose three novel designs to meta-learn DAC policy from offline data.<n>We observe that Q-Mamba achieves competitive or even superior performance to prior online/offline baselines.
  arXiv  Detail & Related papers  (2025-05-04T06:41:43Z)
• COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs [77.79640601822341]
  Large Language Models (LLMs) have demonstrated remarkable success across various domains.<n>Their optimization remains a significant challenge due to the complex and high-dimensional loss landscapes they inhabit.
  arXiv  Detail & Related papers  (2025-02-24T18:42:19Z)
• Locality-aware Surrogates for Gradient-based Black-box Optimization [5.541187309945154]
  We propose locality-aware surrogate models for model-based black-box optimization.<n>We first establish a theoretical connection between gradient alignment and the minimization of a Gradient Path Integral Equation loss.<n>We develop a scalable training algorithm that minimizes the GradPIE loss, enabling both offline and online learning.
  arXiv  Detail & Related papers  (2025-01-31T14:28:47Z)
• CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction [77.8576094863446]
  We propose a new detextbfCoupled dutextbfAl-interactive lineatextbfR atttextbfEntion (CARE) mechanism. We first propose an asymmetrical feature decoupling strategy that asymmetrically decouples the learning process for local inductive bias and long-range dependencies. By adopting a decoupled learning way and fully exploiting complementarity across features, our method can achieve both high efficiency and accuracy.
  arXiv  Detail & Related papers  (2024-11-25T07:56:13Z)
• Cost-Sensitive Multi-Fidelity Bayesian Optimization with Transfer of Learning Curve Extrapolation [55.75188191403343]
  We introduce utility, which is a function predefined by each user and describes the trade-off between cost and performance of BO. We validate our algorithm on various LC datasets and found it outperform all the previous multi-fidelity BO and transfer-BO baselines we consider.
  arXiv  Detail & Related papers  (2024-05-28T07:38:39Z)
• Online Convolutional Re-parameterization [51.97831675242173]
  We present online convolutional re- parameterization (OREPA), a two-stage pipeline, aiming to reduce the huge training overhead by squeezing the complex training-time block into a single convolution. Compared with the state-of-the-art re-param models, OREPA is able to save the training-time memory cost by about 70% and accelerate the training speed by around 2x. We also conduct experiments on object detection and semantic segmentation and show consistent improvements on the downstream tasks.
  arXiv  Detail & Related papers  (2022-04-02T09:50:19Z)
• JUMBO: Scalable Multi-task Bayesian Optimization using Offline Data [86.8949732640035]
  We propose JUMBO, an MBO algorithm that sidesteps limitations by querying additional data. We show that it achieves no-regret under conditions analogous to GP-UCB. Empirically, we demonstrate significant performance improvements over existing approaches on two real-world optimization problems.
  arXiv  Detail & Related papers  (2021-06-02T05:03:38Z)

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.