Structural bias in multi-objective optimisation

• URL: http://arxiv.org/abs/2602.06742v1
• Date: Fri, 06 Feb 2026 14:43:28 GMT
• Title: Structural bias in multi-objective optimisation
• Authors: Jakub Kudela, Niki van Stein, Thomas Bäck, Anna V. Kononova,
• Abstract summary: Structural bias (SB) refers to systematic preferences of an optimisation algorithm for particular regions of the search space.<n> SB is studied extensively in single-objective optimisation, but its role in multi-objective optimisation remains largely unexplored.<n>In this paper, we extend the concept of structural bias to the multi-objective setting and propose a methodology to study it in isolation from fitness-driven guidance.
• Score: 5.869782631289138
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Structural bias (SB) refers to systematic preferences of an optimisation algorithm for particular regions of the search space that arise independently of the objective function. While SB has been studied extensively in single-objective optimisation, its role in multi-objective optimisation remains largely unexplored. This is problematic, as dominance relations, diversity preservation and Pareto-based selection mechanisms may introduce or amplify structural effects. In this paper, we extend the concept of structural bias to the multi-objective setting and propose a methodology to study it in isolation from fitness-driven guidance. We introduce a suite of synthetic multi-objective test problems with analytically controlled Pareto fronts and deliberately uninformative objective values. These problems are designed to decouple algorithmic behaviour from problem structure, allowing bias induced purely by algorithmic operators and design choices to be observed. The test suite covers a range of Pareto front shapes, densities and noise levels, enabling systematic analysis of different manifestations of structural bias. We discuss methodological challenges specific to the multi-objective case and outline how existing SB detection approaches can be adapted. This work provides a first step towards behaviour-based benchmarking of multi-objective optimisers, complementing performance-based evaluation and informing more robust algorithm design.

Related papers

• Deep Unfolding: Recent Developments, Theory, and Design Guidelines [99.63555420898554]
  This article provides a tutorial-style overview of deep unfolding, a framework that transforms optimization algorithms into structured, trainable ML architectures.<n>We review the foundations of optimization for inference and for learning, introduce four representative design paradigms for deep unfolding, and discuss the distinctive training schemes that arise from their iterative nature.
  arXiv  Detail & Related papers  (2025-12-03T13:16:35Z)
• From Coefficients to Directions: Rethinking Model Merging with Directional Alignment [66.99062575537555]
  We introduce a unified geometric framework, emphMerging with Directional Alignment (method), which aligns directional structures consistently in both the parameter and feature spaces.<n>Our analysis shows that directional alignment improves structural coherence, and extensive experiments across benchmarks, model scales, and task configurations further validate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2025-11-29T08:40:58Z)
• Preference-Guided Diffusion for Multi-Objective Offline Optimization [64.08326521234228]
  We propose a preference-guided diffusion model for offline multi-objective optimization.<n>Our guidance is a preference model trained to predict the probability that one design dominates another.<n>Our results highlight the effectiveness of classifier-guided diffusion models in generating diverse and high-quality solutions.
  arXiv  Detail & Related papers  (2025-03-21T16:49:38Z)
• Multi-Objective Causal Bayesian Optimization [2.5311562666866494]
  We propose Multi-Objective Causal Bayesian Optimization (MO-CBO) to identify optimal interventions within a known multi-target causal graph.<n>We show that MO-CBO can be decomposed into several traditional multi-objective optimization tasks.<n>The proposed method will be validated on both synthetic and real-world causal graphs.
  arXiv  Detail & Related papers  (2025-02-20T17:26:16Z)
• ParetoLens: A Visual Analytics Framework for Exploring Solution Sets of Multi-objective Evolutionary Algorithms [42.23658218722045]
  This paper introduces a visual analytics framework specifically tailored to enhance the inspection and exploration of solution sets derived from evolutionary algorithms.<n>ParetoLens enables a detailed inspection of solution distributions in both decision and objective spaces through a suite of interactive visual representations.
  arXiv  Detail & Related papers  (2025-01-06T09:04:14Z)
• Constrained Multi-objective Bayesian Optimization through Optimistic Constraints Estimation [10.77641869521259]
  We propose a novel constrained multi-objective Bayesian optimization algorithm COMBOO that balances active learning of the level-set defined on multiple unknowns with multi-objective optimization within the feasible region.<n>We provide both theoretical analysis and empirical evidence, demonstrating the efficacy of our approach on various synthetic benchmarks and real-world applications.
  arXiv  Detail & Related papers  (2024-11-06T03:38:00Z)
• Generalization Bounds of Surrogate Policies for Combinatorial Optimization Problems [53.03951222945921]
  We analyze smoothed (perturbed) policies, adding controlled random perturbations to the direction used by the linear oracle.<n>Our main contribution is a generalization bound that decomposes the excess risk into perturbation bias, statistical estimation error, and optimization error.<n>We illustrate the scope of the results on applications such as vehicle scheduling, highlighting how smoothing enables both tractable training and controlled generalization.
  arXiv  Detail & Related papers  (2024-07-24T12:00:30Z)
• Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment [46.44464839353993]
  We introduce Rewards-in-Context (RiC), which conditions the response of a foundation model on multiple rewards in its prompt context. RiC only requires supervised fine-tuning of a single foundation model and supports dynamic adjustment for user preferences during inference time.
  arXiv  Detail & Related papers  (2024-02-15T18:58:31Z)
• Backpropagation of Unrolled Solvers with Folded Optimization [55.04219793298687]
  The integration of constrained optimization models as components in deep networks has led to promising advances on many specialized learning tasks. One typical strategy is algorithm unrolling, which relies on automatic differentiation through the operations of an iterative solver. This paper provides theoretical insights into the backward pass of unrolled optimization, leading to a system for generating efficiently solvable analytical models of backpropagation.
  arXiv  Detail & Related papers  (2023-01-28T01:50:42Z)
• A Pareto-optimal compositional energy-based model for sampling and optimization of protein sequences [55.25331349436895]
  Deep generative models have emerged as a popular machine learning-based approach for inverse problems in the life sciences. These problems often require sampling new designs that satisfy multiple properties of interest in addition to learning the data distribution.
  arXiv  Detail & Related papers  (2022-10-19T19:04:45Z)
• An Instance Space Analysis of Constrained Multi-Objective Optimization Problems [1.314903445595385]
  We explore the relationship between constrained multi-objective evolutionary algorithms (CMOEAs) performance and CMOP instances characteristics using Instance Space Analysis (ISA) Detailed evaluation of problem-algorithm footprints spanning six CMOP benchmark suites and fifteen CMOEAs is presented. We conclude that two key characteristics, the isolation of non-dominate set and the correlation between constraints and objectives evolvability, have the greatest impact on algorithm performance.
  arXiv  Detail & Related papers  (2022-03-02T04:28:11Z)
• Empirical Study on the Benefits of Multiobjectivization for Solving Single-Objective Problems [0.0]
  Local optima are often preventing algorithms from making progress and thus pose a severe threat. With the use of a sophisticated visualization technique based on the multi-objective gradients, the properties of the arising multi-objective landscapes are illustrated and examined. We will empirically show that the multi-objective COCO MOGSA is able to exploit these properties to overcome local traps.
  arXiv  Detail & Related papers  (2020-06-25T14:04:37Z)

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.