Revealing Domain-Spatiality Patterns for Configuration Tuning: Domain Knowledge Meets Fitness Landscapes

Configuration tuning for better performance is crucial in quality assurance. Yet, there has long been a mystery on tuners' effectiveness, due to the black-box nature of configurable systems. Prior efforts predominantly adopt static domain analysis (e.g., static taint analysis), which often lacks generalizability, or dynamic data analysis (e.g., benchmarking performance analysis), limiting explainability. In this work, we embrace Fitness Landscape Analysis (FLA) as a bridge between domain knowledge and difficulty of the tuning. We propose Domland, a two-pronged methodology that synergizes the spatial information obtained from FLA and domain-driven analysis to systematically capture the hidden characteristics of configuration tuning cases, explaining how and why a tuner might succeed or fail. This helps to better interpret and contextualize the behavior of tuners and inform tuner design. To evaluate Domland, we conduct a case study of nine software systems and 93 workloads, from which we reveal several key findings: (1) configuration landscapes are inherently system-specific, with no single domain factor (e.g., system area, programming language, or resource intensity) consistently shaping their structure; (2) the core options (e.g., pic-struct of x264), which control the main functional flows, exert a stronger influence on landscape ruggedness (i.e. the difficulty of tuning) compared to resource options (e.g., cpu-independent of x264); (3) Workload effects on landscape structure are not uniformly tied to type or scale. Both contribute to landscape variations, but their impact is system-dependent.

Variable Search Stepsize for Randomized Local Search in Multi-Objective Combinatorial Optimization

Over the past two decades, research in evolutionary multi-objective optimization has predominantly focused on continuous domains, with comparatively limited attention given to multi-objective combinatorial optimization problems (MOCOPs). Combinatorial problems differ significantly from continuous ones in terms of problem structure and landscape. Recent studies have shown that on MOCOPs multi-objective evolutionary algorithms (MOEAs) can even be outperformed by simple randomised local search. Starting with a randomly sampled solution in search space, randomised local search iteratively draws a random solution (from an archive) to perform local variation within its neighbourhood. However, in most existing methods, the local variation relies on a fixed neighbourhood, which limits exploration and makes the search easy to get trapped in local optima. In this paper, we present a simple yet effective local search method, called variable stepsize randomized local search (VS-RLS), which adjusts the stepsize during the search. VS-RLS transitions gradually from a broad, exploratory search in the early phases to a more focused, fine-grained search as the search progresses. We demonstrate the effectiveness and generalizability of VS-RLS through extensive evaluations against local search and MOEAs methods on diverse MOCOPs.

Random is Faster than Systematic in Multi-Objective Local Search

Local search is a fundamental method in operations research and combinatorial optimisation. It has been widely applied to a variety of challenging problems, including multi-objective optimisation where multiple, often conflicting, objectives need to be simultaneously considered. In multi-objective local search algorithms, a common practice is to maintain an archive of all non-dominated solutions found so far, from which the algorithm iteratively samples a solution to explore its neighbourhood. A central issue in this process is how to explore the neighbourhood of a selected solution. In general, there are two main approaches: 1) systematic exploration and 2) random sampling. The former systematically explores the solution's neighbours until a stopping condition is met -- for example, when the neighbourhood is exhausted (i.e., the best improvement strategy) or once a better solution is found (i.e., first improvement). In contrast, the latter randomly selects and evaluates only one neighbour of the solution. One may think systematic exploration may be more efficient, as it prevents from revisiting the same neighbours multiple times. In this paper, however, we show that this may not be the case. We first empirically demonstrate that the random sampling method is consistently faster than the systematic exploration method across a range of multi-objective problems. We then give an intuitive explanation for this phenomenon using toy examples, showing that the superior performance of the random sampling method relies on the distribution of ``good neighbours''. Next, we show that the number of such neighbours follows a certain probability distribution during the search. Lastly, building on this distribution, we provide a theoretical insight for why random sampling is more efficient than systematic exploration, regardless of whether the best improvement or first improvement strategy is used.

Uncertainty-Aware Dual-Ranking Strategy for Offline Data-Driven Multi-Objective Optimization

Offline data-driven Multi-Objective Optimization Problems (MOPs) rely on limited data from simulations, experiments, or sensors. This scarcity leads to high epistemic uncertainty in surrogate predictions. Conventional surrogate methods such as Kriging assume Gaussian distributions, which can yield suboptimal results when the assumptions fail. To address these issues, we propose a simple yet novel dual-ranking strategy, working with a basic multi-objective evolutionary algorithm, NSGA-II, where the built-in non-dominated sorting is kept and the second rank is devised for uncertainty estimation. In the latter, we utilize the uncertainty estimates given by several surrogate models, including Quantile Regression (QR), Monte Carlo Dropout (MCD), and Bayesian Neural Networks (BNNs). Concretely, with this dual-ranking strategy, each solution's final rank is the average of its non-dominated sorting rank and a rank derived from the uncertainty-adjusted fitness function, thus reducing the risk of misguided optimization under data constraints. We evaluate our approach on benchmark and real-world MOPs, comparing it to state-of-the-art methods. The results show that our dual-ranking strategy significantly improves the performance of NSGA-II in offline settings, achieving competitive outcomes compared with traditional surrogate-based methods. This framework advances uncertainty-aware multi-objective evolutionary algorithms, offering a robust solution for data-limited, real-world applications.

Not Just for Archiving: Provable Benefits of Reusing the Archive in Evolutionary Multi-objective Optimization

Evolutionary Algorithms (EAs) have become the most popular tool for solving widely-existed multi-objective optimization problems. In Multi-Objective EAs (MOEAs), there is increasing interest in using an archive to store non-dominated solutions generated during the search. This approach can 1) mitigate the effects of population oscillation, a common issue in many MOEAs, and 2) allow for the use of smaller, more practical population sizes. In this paper, we analytically show that the archive can even further help MOEAs through reusing its solutions during the process of new solution generation. We first prove that using a small population size alongside an archive (without incorporating archived solutions in the generation process) may fail on certain problems, as the population may remove previously discovered but promising solutions. We then prove that reusing archive solutions can overcome this limitation, resulting in at least a polynomial speedup on the expected running time. Our analysis focuses on the well-established SMS-EMOA algorithm applied to the commonly studied OneJumpZeroJump problem as well as one of its variants. We also show that reusing archive solutions can be better than using a large population size directly. Finally, we show that our theoretical findings can generally hold in practice by experiments on four well-known practical optimization problems -- multi-objective 0-1 Knapsack, TSP, QAP and NK-landscape problems -- with realistic settings.

When to Truncate the Archive? On the Effect of the Truncation Frequency in Multi-Objective Optimisation

Using an archive to store nondominated solutions found during the search of a multi-objective evolutionary algorithm (MOEA) is a useful practice. However, as nondominated solutions of a multi-objective optimisation problem can be enormous or infinitely many, it is desirable to provide the decision-maker with only a small, representative portion of all the nondominated solutions in the archive, thus entailing a truncation operation. Then, an important issue is when to truncate the archive. This can be done once a new solution generated, a batch of new solutions generated, or even using an unbounded archive to keep all nondominated solutions generated and truncate it later. Intuitively, the last approach may lead to a better result since we have all the information in hand before performing the truncation. In this paper, we study this issue and investigate the effect of the timing of truncating the archive. We apply well-established truncation criteria that are commonly used in the population maintenance procedure of MOEAs (e.g., crowding distance, hypervolume indicator, and decomposition). We show that, interestingly, truncating the archive once a new solution generated tends to be the best, whereas considering an unbounded archive is often the worst. We analyse and discuss this phenomenon. Our results highlight the importance of developing effective subset selection techniques (rather than employing the population maintenance methods in MOEAs) when using a large archive.

Multi-objective Pseudo Boolean Functions in Runtime Analysis: A Review

Recently, there has been growing interest within the theoretical community in analytically studying multi-objective evolutionary algorithms. This runtime analysis-focused research can help formally understand algorithm behaviour, explain empirical observations, and provide theoretical insights to support algorithm development and exploration. However, the test problems commonly used in the theoretical analysis are predominantly limited to problems with heavy ``artificial'' characteristics (e.g., symmetric objectives and linear Pareto fronts), which may not be able to well represent realistic scenarios. In this paper, we survey commonly used multi-objective functions in the theory domain and systematically review their features, limitations and implications to practical use. Moreover, we present several new functions with more realistic features, such as local optimality and nonlinearity of the Pareto front, through simply mixing and matching classical single-objective functions in the area (e.g., LeadingOnes, Jump and RoyalRoad). We hope these functions can enrich the existing test problem suites, and strengthen the connection between theoretic and practical research.

A Weight Adaptation Trigger Mechanism in Decomposition-based Evolutionary Multi-Objective Optimisation

Decomposition-based multi-objective evolutionary algorithms (MOEAs) are widely used for solving multi-objective optimisation problems. However, their effectiveness depends on the consistency between the problems Pareto front shape and the weight distribution. Decomposition-based MOEAs, with uniformly distributed weights (in a simplex), perform well on problems with a regular (simplex-like) Pareto front, but not on those with an irregular Pareto front. Previous studies have focused on adapting the weights to approximate the irregular Pareto front during the evolutionary process. However, these adaptations can actually harm the performance on the regular Pareto front via changing the weights during the search process that are eventually the best fit for the Pareto front. In this paper, we propose an algorithm called the weight adaptation trigger mechanism for decomposition-based MOEAs (ATM-MOEA/D) to tackle this issue. ATM-MOEA/D uses an archive to gradually approximate the shape of the Pareto front during the search. When the algorithm detects evolution stagnation (meaning the population no longer improves significantly), it compares the distribution of the population with that of the archive to distinguish between regular and irregular Pareto fronts. Only when an irregular Pareto front is identified, the weights are adapted. Our experimental results show that the proposed algorithm not only performs generally better than seven state-of-the-art weight-adapting methods on irregular Pareto fronts but also is able to achieve the same results as fixed-weight methods like MOEA/D on regular Pareto fronts.

Stochastic Population Update Provably Needs An Archive in Evolutionary Multi-objective Optimization

Evolutionary algorithms (EAs) have been widely applied to multi-objective optimization, due to their nature of population-based search. Population update, a key component in multi-objective EAs (MOEAs), is usually performed in a greedy, deterministic manner. However, recent studies have questioned this practice and shown that stochastic population update (SPU), which allows inferior solutions have a chance to be preserved, can help MOEAs jump out of local optima more easily. While introducing randomness in the population update process boosts the exploration of MOEAs, there is a drawback that the population may not always preserve the very best solutions found, thus entailing a large population. Intuitively, a possible solution to this issue is to introduce an archive that stores the best solutions ever found. In this paper, we theoretically show that using an archive can allow a small population and accelerate the search of SPU-based MOEAs substantially. Specifically, we analyze the expected running time of two well-established MOEAs, SMS-EMOA and NSGA-II, with SPU for solving a commonly studied bi-objective problem OneJumpZeroJump, and prove that using an archive can bring (even exponential) speedups. The comparison between SMS-EMOA and NSGA-II also suggests that the $(\mu+\mu)$ update mode may be more suitable for SPU than the $(\mu+1)$ update mode. Furthermore, our derived running time bounds for using SPU alone are significantly tighter than previously known ones. Our theoretical findings are also empirically validated on a well-known practical problem, the multi-objective traveling salesperson problem. We hope this work may provide theoretical support to explore different ideas of designing algorithms in evolutionary multi-objective optimization.

Distilled Lifelong Self-Adaptation for Configurable Systems

Modern configurable systems provide tremendous opportunities for engineering future intelligent software systems. A key difficulty thereof is how to effectively self-adapt the configuration of a running system such that its performance (e.g., runtime and throughput) can be optimized under time-varying workloads. This unfortunately remains unaddressed in existing approaches as they either overlook the available past knowledge or rely on static exploitation of past knowledge without reasoning the usefulness of information when planning for self-adaptation. In this paper, we tackle this challenging problem by proposing DLiSA, a framework that self-adapts configurable systems. DLiSA comes with two properties: firstly, it supports lifelong planning, and thereby the planning process runs continuously throughout the lifetime of the system, allowing dynamic exploitation of the accumulated knowledge for rapid adaptation. Secondly, the planning for a newly emerged workload is boosted via distilled knowledge seeding, in which the knowledge is dynamically purified such that only useful past configurations are seeded when necessary, mitigating misleading information. Extensive experiments suggest that the proposed DLiSA significantly outperforms state-of-the-art approaches, demonstrating a performance improvement of up to 229% and a resource acceleration of up to 2.22x on generating promising adaptation configurations. All data and sources can be found at our repository: https://github.com/ideas-labo/dlisa.