Preference-Driven Multi-Objective Combinatorial Optimization with Conditional Computation

• URL: http://arxiv.org/abs/2506.08898v2
• Date: Fri, 20 Jun 2025 08:04:32 GMT
• Title: Preference-Driven Multi-Objective Combinatorial Optimization with Conditional Computation
• Authors: Mingfeng Fan, Jianan Zhou, Yifeng Zhang, Yaoxin Wu, Jinbiao Chen, Guillaume Adrien Sartoretti,
• Abstract summary: POCCO is a novel plug-and-play framework that enables adaptive selection of model structures for subproblems.<n>We propose a preference-driven optimization algorithm that learns pairwise preferences between winning and losing solutions.
• Score: 10.153136816705542
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent deep reinforcement learning methods have achieved remarkable success in solving multi-objective combinatorial optimization problems (MOCOPs) by decomposing them into multiple subproblems, each associated with a specific weight vector. However, these methods typically treat all subproblems equally and solve them using a single model, hindering the effective exploration of the solution space and thus leading to suboptimal performance. To overcome the limitation, we propose POCCO, a novel plug-and-play framework that enables adaptive selection of model structures for subproblems, which are subsequently optimized based on preference signals rather than explicit reward values. Specifically, we design a conditional computation block that routes subproblems to specialized neural architectures. Moreover, we propose a preference-driven optimization algorithm that learns pairwise preferences between winning and losing solutions. We evaluate the efficacy and versatility of POCCO by applying it to two state-of-the-art neural methods for MOCOPs. Experimental results across four classic MOCOP benchmarks demonstrate its significant superiority and strong generalization.

Related papers

• Preference Optimization for Combinatorial Optimization Problems [54.87466279363487]
  Reinforcement Learning (RL) has emerged as a powerful tool for neural optimization, enabling models learns that solve complex problems without requiring expert knowledge.<n>Despite significant progress, existing RL approaches face challenges such as diminishing reward signals and inefficient exploration in vast action spaces.<n>We propose Preference Optimization, a novel method that transforms quantitative reward signals into qualitative preference signals via statistical comparison modeling.
  arXiv  Detail & Related papers  (2025-05-13T16:47:00Z)
• Scalable Min-Max Optimization via Primal-Dual Exact Pareto Optimization [66.51747366239299]
  We propose a smooth variant of the min-max problem based on the augmented Lagrangian.<n>The proposed algorithm scales better with the number of objectives than subgradient-based strategies.
  arXiv  Detail & Related papers  (2025-03-16T11:05:51Z)
• LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning [56.273799410256075]
  The framework combines Monte Carlo Tree Search (MCTS) with iterative Self-Refine to optimize the reasoning path. The framework has been tested on general and advanced benchmarks, showing superior performance in terms of search efficiency and problem-solving capability.
  arXiv  Detail & Related papers  (2024-10-03T18:12:29Z)
• Optimizing Solution-Samplers for Combinatorial Problems: The Landscape of Policy-Gradient Methods [52.0617030129699]
  We introduce a novel theoretical framework for analyzing the effectiveness of DeepMatching Networks and Reinforcement Learning methods. Our main contribution holds for a broad class of problems including Max-and Min-Cut, Max-$k$-Bipartite-Bi, Maximum-Weight-Bipartite-Bi, and Traveling Salesman Problem. As a byproduct of our analysis we introduce a novel regularization process over vanilla descent and provide theoretical and experimental evidence that it helps address vanishing-gradient issues and escape bad stationary points.
  arXiv  Detail & Related papers  (2023-10-08T23:39:38Z)
• Optimization and Optimizers for Adversarial Robustness [10.279287131070157]
  In this paper, we introduce a novel framework that blends a general-purpose constrained-optimization solver with Constraint Folding. Regarding reliability, PWCF provides solutions with stationarity measures and feasibility tests to assess the solution quality. We further explore the distinct patterns in the solutions found for solving these problems using various combinations of losses, perturbation models, and optimization algorithms.
  arXiv  Detail & Related papers  (2023-03-23T16:22:59Z)
• Linearization Algorithms for Fully Composite Optimization [61.20539085730636]
  This paper studies first-order algorithms for solving fully composite optimization problems convex compact sets. We leverage the structure of the objective by handling differentiable and non-differentiable separately, linearizing only the smooth parts.
  arXiv  Detail & Related papers  (2023-02-24T18:41:48Z)
• An Empirical Evaluation of Zeroth-Order Optimization Methods on AI-driven Molecule Optimization [78.36413169647408]
  We study the effectiveness of various ZO optimization methods for optimizing molecular objectives. We show the advantages of ZO sign-based gradient descent (ZO-signGD) We demonstrate the potential effectiveness of ZO optimization methods on widely used benchmark tasks from the Guacamol suite.
  arXiv  Detail & Related papers  (2022-10-27T01:58:10Z)
• A Study of Scalarisation Techniques for Multi-Objective QUBO Solving [0.0]
  Quantum and quantum-inspired optimisation algorithms have shown promising performance when applied to academic benchmarks as well as real-world problems. However, QUBO solvers are single objective solvers. To make them more efficient at solving problems with multiple objectives, a decision on how to convert such multi-objective problems to single-objective problems need to be made.
  arXiv  Detail & Related papers  (2022-10-20T14:54:37Z)
• Pareto Set Learning for Neural Multi-objective Combinatorial Optimization [6.091096843566857]
  Multiobjective optimization (MOCO) problems can be found in many real-world applications. We develop a learning-based approach to approximate the whole Pareto set for a given MOCO problem without further search procedure. Our proposed method significantly outperforms some other methods on the multiobjective traveling salesman problem, multiconditioned vehicle routing problem and multi knapsack problem in terms of solution quality, speed, and model efficiency.
  arXiv  Detail & Related papers  (2022-03-29T09:26:22Z)
• A novel multiobjective evolutionary algorithm based on decomposition and multi-reference points strategy [14.102326122777475]
  Multiobjective evolutionary algorithm based on decomposition (MOEA/D) has been regarded as a significantly promising approach for solving multiobjective optimization problems (MOPs) We propose an improved MOEA/D algorithm by virtue of the well-known Pascoletti-Serafini scalarization method and a new strategy of multi-reference points.
  arXiv  Detail & Related papers  (2021-10-27T02:07:08Z)
• Batched Data-Driven Evolutionary Multi-Objective Optimization Based on Manifold Interpolation [6.560512252982714]
  We propose a framework for implementing batched data-driven evolutionary multi-objective optimization. It is so general that any off-the-shelf evolutionary multi-objective optimization algorithms can be applied in a plug-in manner. Our proposed framework is featured with a faster convergence and a stronger resilience to various PF shapes.
  arXiv  Detail & Related papers  (2021-09-12T23:54:26Z)

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.