Richard Allmendinger

Youngmin Kim, Richard Allmendinger, Manuel López-Ibáñez

We consider a type of constrained optimization problem, where the violation of a constraint leads to an irrevocable loss, such as breakage of a valuable experimental resource/platform or loss of human life. Such problems are referred to as safe optimization problems (SafeOPs). While SafeOPs have received attention in the machine learning community in recent years, there was little interest in the evolutionary computation (EC) community despite some early attempts between 2009 and 2011. Moreover, there is a lack of acceptable guidelines on how to benchmark different algorithms for SafeOPs, an area where the EC community has significant experience in. Driven by the need for more efficient algorithms and benchmark guidelines for SafeOPs, the objective of this paper is to reignite the interest of this problem class in the EC community. To achieve this we (i) provide a formal definition of SafeOPs and contrast it to other types of optimization problems that the EC community is familiar with, (ii) investigate the impact of key SafeOP parameters on the performance of selected safe optimization algorithms, (iii) benchmark EC against state-of-the-art safe optimization algorithms from the machine learning community, and (iv) provide an open-source Python framework to replicate and extend our work.

Mayowa Ayodele, Richard Allmendinger, Manuel López-Ibáñez et al.

Quantum and quantum-inspired optimisation algorithms are designed to solve problems represented in binary, quadratic and unconstrained form. Combinatorial optimisation problems are therefore often formulated as Quadratic Unconstrained Binary Optimisation Problems (QUBO) to solve them with these algorithms. Moreover, these QUBO solvers are often implemented using specialised hardware to achieve enormous speedups, e.g. Fujitsu's Digital Annealer (DA) and D-Wave's Quantum Annealer. However, these are single-objective solvers, while many real-world problems feature multiple conflicting objectives. Thus, a common practice when using these QUBO solvers is to scalarise such multi-objective problems into a sequence of single-objective problems. Due to design trade-offs of these solvers, formulating each scalarisation may require more time than finding a local optimum. We present the first attempt to extend the algorithm supporting a commercial QUBO solver as a multi-objective solver that is not based on scalarisation. The proposed multi-objective DA algorithm is validated on the bi-objective Quadratic Assignment Problem. We observe that algorithm performance significantly depends on the archiving strategy adopted, and that combining DA with non-scalarisation methods to optimise multiple objectives outperforms the current scalarised version of the DA in terms of final solution quality.

Chin Woei Lim, Richard Allmendinger, Joshua Knowles et al. · cambridge

We use a multi-agent system to model how agents (representing firms) may collaborate and adapt in a business 'landscape' where some, more influential, firms are given the power to shape the landscape of other firms. The landscapes we study are based on the well-known NK model of Kauffman, with the addition of 'shapers', firms that can change the landscape's features for themselves and all other players. Our work investigates how firms that are additionally endowed with cognitive and experiential search, and the ability to form collaborations with other firms, can use these capabilities to adapt more quickly and adeptly. We find that, in a collaborative group, firms must still have a mind of their own and resist direct mimicry of stronger partners to attain better heights collectively. Larger groups and groups with more influential members generally do better, so targeted intelligent cooperation is beneficial. These conclusions are tentative, and our results show a sensitivity to landscape ruggedness and "malleability" (i.e. the capacity of the landscape to be changed by the shaper firms). Overall, our work demonstrates the potential of computer science, evolution, and machine learning to contribute to business strategy in these complex environments.

Claire Little, Mark Elliot, Richard Allmendinger

Most statistical agencies release randomly selected samples of Census microdata, usually with sample fractions under 10% and with other forms of statistical disclosure control (SDC) applied. An alternative to SDC is data synthesis, which has been attracting growing interest, yet there is no clear consensus on how to measure the associated utility and disclosure risk of the data. The ability to produce synthetic Census microdata, where the utility and associated risks are clearly understood, could mean that more timely and wider-ranging access to microdata would be possible. This paper follows on from previous work by the authors which mapped synthetic Census data on a risk-utility (R-U) map. The paper presents a framework to measure the utility and disclosure risk of synthetic data by comparing it to samples of the original data of varying sample fractions, thereby identifying the sample fraction which has equivalent utility and risk to the synthetic data. Three commonly used data synthesis packages are compared with some interesting results. Further work is needed in several directions but the methodology looks very promising.

Mayowa Ayodele, Richard Allmendinger, Manuel López-Ibáñez et al.

In recent years, there has been significant research interest in solving Quadratic Unconstrained Binary Optimisation (QUBO) problems. Physics-inspired optimisation algorithms have been proposed for deriving optimal or sub-optimal solutions to QUBOs. These methods are particularly attractive within the context of using specialised hardware, such as quantum computers, application specific CMOS and other high performance computing resources for solving optimisation problems. These solvers are then applied to QUBO formulations of combinatorial optimisation problems. 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. In this study, we compare methods of deriving scalarisation weights when combining two objectives of the cardinality constrained mean-variance portfolio optimisation problem into one. We show significant performance improvement (measured in terms of hypervolume) when using a method that iteratively fills the largest space in the Pareto front compared to a näive approach using uniformly generated weights.

Alma Rahat, Tinkle Chugh, Jonathan Fieldsend et al.

Many methods for performing multi-objective optimisation of computationally expensive problems have been proposed recently. Typically, a probabilistic surrogate for each objective is constructed from an initial dataset. The surrogates can then be used to produce predictive densities in the objective space for any solution. Using the predictive densities, we can compute the expected hypervolume improvement (EHVI) due to a solution. Maximising the EHVI, we can locate the most promising solution that may be expensively evaluated next. There are closed-form expressions for computing the EHVI, integrating over the multivariate predictive densities. However, they require partitioning the objective space, which can be prohibitively expensive for more than three objectives. Furthermore, there are no closed-form expressions for a problem where the predictive densities are dependent, capturing the correlations between objectives. Monte Carlo approximation is used instead in such cases, which is not cheap. Hence, the need to develop new accurate but cheaper approximation methods remains. Here we investigate an alternative approach toward approximating the EHVI using Gauss-Hermite quadrature. We show that it can be an accurate alternative to Monte Carlo for both independent and correlated predictive densities with statistically significant rank correlations for a range of popular test problems.

Samantha Petersone, Alwin Tan, Richard Allmendinger et al.

The core activity of a Private Equity (PE) firm is to invest into companies in order to provide the investors with profit, usually within 4-7 years. To invest into a company or not is typically done manually by looking at various performance indicators of the company and then making a decision often based on instinct. This process is rather unmanageable given the large number of companies to potentially invest. Moreover, as more data about company performance indicators becomes available and the number of different indicators one may want to consider increases, manual crawling and assessment of investment opportunities becomes inefficient and ultimately impossible. To address these issues, this paper proposes a framework for automated data-driven screening of investment opportunities and thus the recommendation of businesses to invest in. The framework draws on data from several sources to assess the financial and managerial position of a company, and then uses an explainable artificial intelligence (XAI) engine to suggest investment recommendations. The robustness of the model is validated using different AI algorithms, class imbalance-handling methods, and features extracted from the available data sources.

Danny Wood, Theodore Papamarkou, Matt Benatan et al.

In order to trust the predictions of a machine learning algorithm, it is necessary to understand the factors that contribute to those predictions. In the case of probabilistic and uncertainty-aware models, it is necessary to understand not only the reasons for the predictions themselves, but also the reasons for the model's level of confidence in those predictions. In this paper, we show how existing methods in explainability can be extended to uncertainty-aware models and how such extensions can be used to understand the sources of uncertainty in a model's predictive distribution. In particular, by adapting permutation feature importance, partial dependence plots, and individual conditional expectation plots, we demonstrate that novel insights into model behaviour may be obtained and that these methods can be used to measure the impact of features on both the entropy of the predictive distribution and the log-likelihood of the ground truth labels under that distribution. With experiments using both synthetic and real-world data, we demonstrate the utility of these approaches to understand both the sources of uncertainty and their impact on model performance.

Bahrul Ilmi Nasution, Floor Eijkelboom, Mark Elliot et al.

Synthetic data generation is an important tool for privacy-preserving data sharing. While diffusion models have set recent benchmarks, flow matching (FM) offers a promising alternative. This paper presents different ways to implement flow matching for tabular data synthesis. We provide a comprehensive empirical study that compares flow matching (FM and variational FM) with a state-of-the-art diffusion method (TabDDPM and TabSyn) in tabular data synthesis. We evaluate both the standard Optimal Transport (OT) and the Variance Preserving (VP) probability paths, and also compare deterministic and stochastic samplers -- something possible when learning to generate using \textit{variational} flow matching -- characterising the empirical relationship between data utility and privacy risk. Our key findings reveal that flow matching, particularly TabbyFlow, outperforms diffusion baselines. Flow matching methods also achieves better performance with remarkably low function evaluations ($\leq$ 100 steps), offering a substantial computational advantage. The choice of probability path is also crucial, as using the OT path demonstrates superior performance, while VP has potential for producing synthetic data with lower disclosure risk. Lastly, our results show that making flows stochastic not only preserves marginal distributions but, in some instances, enables the generation of high utility synthetic data with reduced disclosure risk.

Nian Ran, Peng Xiao, Yue Wang et al.

The application of large deep learning models in weather forecasting has led to significant advancements in the field, including higher-resolution forecasting and extended prediction periods exemplified by models such as Pangu and Fuxi. Despite these successes, previous research has largely been characterized by the neglect of extreme weather events, and the availability of datasets specifically curated for such events remains limited. Given the critical importance of accurately forecasting extreme weather, this study introduces a comprehensive dataset that incorporates high-resolution extreme weather cases derived from the High-Resolution Rapid Refresh (HRRR) data, a 3-km real-time dataset provided by NOAA. We also evaluate the current state-of-the-art deep learning models and Numerical Weather Prediction (NWP) systems on HR-Extreme, and provide a improved baseline deep learning model called HR-Heim which has superior performance on both general loss and HR-Extreme compared to others. Our results reveal that the errors of extreme weather cases are significantly larger than overall forecast error, highlighting them as an crucial source of loss in weather prediction. These findings underscore the necessity for future research to focus on improving the accuracy of extreme weather forecasts to enhance their practical utility.

Nian Ran, Bahrul Ilmi Nasution, Claire Little et al.

Synthetic data has a key role to play in data sharing by statistical agencies and other generators of statistical data products. Generative Adversarial Networks (GANs), typically applied to image synthesis, are also a promising method for tabular data synthesis. However, there are unique challenges in tabular data compared to images, eg tabular data may contain both continuous and discrete variables and conditional sampling, and, critically, the data should possess high utility and low disclosure risk (the risk of re-identifying a population unit or learning something new about them), providing an opportunity for multi-objective (MO) optimization. Inspired by MO GANs for images, this paper proposes a smart MO evolutionary conditional tabular GAN (SMOE-CTGAN). This approach models conditional synthetic data by applying conditional vectors in training, and uses concepts from MO optimisation to balance disclosure risk against utility. Our results indicate that SMOE-CTGAN is able to discover synthetic datasets with different risk and utility levels for multiple national census datasets. We also find a sweet spot in the early stage of training where a competitive utility and extremely low risk are achieved, by using an Improvement Score. The full code can be downloaded from https://github.com/HuskyNian/SMO\_EGAN\_pytorch.

Bahrul Ilmi Nasution, Mark Elliot, Richard Allmendinger

Generative Adversarial Networks (GAN) have been used in many studies to synthesise mixed tabular data. Conditional tabular GAN (CTGAN) have been the most popular variant but struggle to effectively navigate the risk-utility trade-off. Bayesian GAN have received less attention for tabular data, but have been explored with unstructured data such as images and text. The most used technique employed in Bayesian GAN is Markov Chain Monte Carlo (MCMC), but it is computationally intensive, particularly in terms of weight storage. In this paper, we introduce Gaussian Approximation of CTGAN (GACTGAN), an integration of the Bayesian posterior approximation technique using Stochastic Weight Averaging-Gaussian (SWAG) within the CTGAN generator to synthesise tabular data, reducing computational overhead after the training phase. We demonstrate that GACTGAN yields better synthetic data compared to CTGAN, achieving better preservation of tabular structure and inferential statistics with less privacy risk. These results highlight GACTGAN as a simpler, effective implementation of Bayesian tabular synthesis.

Amr Mousa, Neil Karavis, Michele Caprio et al.

Quadrupedal locomotion via Reinforcement Learning (RL) is commonly addressed using the teacher-student paradigm, where a privileged teacher guides a proprioceptive student policy. However, key challenges such as representation misalignment between privileged teacher and proprioceptive-only student, covariate shift due to behavioral cloning, and lack of deployable adaptation; lead to poor generalization in real-world scenarios. We propose Teacher-Aligned Representations via Contrastive Learning (TAR), a framework that leverages privileged information with self-supervised contrastive learning to bridge this gap. By aligning representations to a privileged teacher in simulation via contrastive objectives, our student policy learns structured latent spaces and exhibits robust generalization to Out-of-Distribution (OOD) scenarios, surpassing the fully privileged "Teacher". Results showed accelerated training by 2x compared to state-of-the-art baselines to achieve peak performance. OOD scenarios showed better generalization by 40% on average compared to existing methods. Moreover, TAR transitions seamlessly into learning during deployment without requiring privileged states, setting a new benchmark in sample-efficient, adaptive locomotion and enabling continual fine-tuning in real-world scenarios. Open-source code and videos are available at https://amrmousa.com/TARLoco/.

Tasos Asonitis, Richard Allmendinger, Matt Benatan et al.

We propose SonOpt, the first (open source) data sonification application for monitoring the progress of bi-objective population-based optimization algorithms during search, to facilitate algorithm understanding. SonOpt provides insights into convergence/stagnation of search, the evolution of the approximation set shape, location of recurring points in the approximation set, and population diversity. The benefits of data sonification have been shown for various non-optimization related monitoring tasks. However, very few attempts have been made in the context of optimization and their focus has been exclusively on single-objective problems. In comparison, SonOpt is designed for bi-objective optimization problems, relies on objective function values of non-dominated solutions only, and is designed with the user (listener) in mind; avoiding convolution of multiple sounds and prioritising ease of familiarizing with the system. This is achieved using two sonification paths relying on the concepts of wavetable and additive synthesis. This paper motivates and describes the architecture of SonOpt, and then validates SonOpt for two popular multi-objective optimization algorithms (NSGA-II and MOEA/D). Experience SonOpt yourself via https://github.com/tasos-a/SonOpt-1.0 .

Nian Ran, Yue Wang, Xiaoyuan Zhang et al.

Molecular design involves an enormous and irregular search space, where traditional optimizers such as Bayesian optimization, genetic algorithms, and generative models struggle to leverage expert knowledge or handle complex feedback. Recently, LLMs have been used as optimizers, achieving promising results on benchmarks such as PMO. However, existing approaches rely only on prompting or extra training, without mechanisms to handle complex feedback or maintain scalable memory. In particular, the common practice of appending or summarizing experiences at every query leads to redundancy, degraded exploration, and ultimately poor final outcomes under large-scale iterative search. We introduce ExLLM (Experience-Enhanced LLM optimization), an LLM-as-optimizer framework with three components: (1) a compact, evolving experience snippet tailored to large discrete spaces that distills non-redundant cues and improves convergence at low cost; (2) a simple yet effective k-offspring scheme that widens exploration per call and reduces orchestration cost; and (3) a lightweight feedback adapter that normalizes objectives for selection while formatting constraints and expert hints for iteration. ExLLM sets new state-of-the-art results on PMO and generalizes strongly in our setup, it sets records on circle packing and stellarator design, and yields consistent gains across additional domains requiring only a task-description template and evaluation functions to transfer.

Qiyu Wei, Haowei Wang, Zirui Cao et al.

Bayesian optimization (BO) is an effective technique for black-box optimization. However, its applicability is typically limited to moderate-budget problems due to the cubic complexity of fitting the Gaussian process (GP) surrogate model. In large-budget scenarios, directly employing the standard GP model faces significant challenges in computational time and resource requirements. In this paper, we propose a novel approach, gradient-based sample selection Bayesian Optimization (GSSBO), to enhance the computational efficiency of BO. The GP model is constructed on a selected set of samples instead of the whole dataset. These samples are selected by leveraging gradient information to remove redundancy while preserving diversity and representativeness. We provide a theoretical analysis of the gradient-based sample selection strategy and obtain explicit sublinear regret bounds for our proposed framework. Extensive experiments on synthetic and real-world tasks demonstrate that our approach significantly reduces the computational cost of GP fitting in BO while maintaining optimization performance comparable to baseline methods.

Nian Ran, Fayez M. Al-Alweet, Richard Allmendinger et al.

In multiphase flow systems, classifying flow patterns is crucial to optimize fluid dynamics and enhance system efficiency. Current industrial methods and scientific laboratories mainly depend on techniques such as flow visualization using regular cameras or the naked eye, as well as high-speed imaging at elevated flow rates. These methods are limited by their reliance on subjective interpretations and are particularly applicable in transparent pipes. Consequently, conventional techniques usually achieve context-dependent accuracy rates and often lack generalizability. This study introduces a novel platform that integrates a capacitance sensor and AI-driven classification methods, benchmarked against traditional techniques. Experimental results demonstrate that the proposed approach, utilizing a 1D SENet deep learning model, achieves over 85\% accuracy on experiment-based datasets and 71\% accuracy on pattern-based datasets. These results highlight significant improvements in robustness and reliability compared to existing methodologies. This work offers a transformative pathway for real-time flow monitoring and predictive modeling, addressing key challenges in industrial applications.

Qiyu Wei, Haowei Wang, Richard Allmendinger et al.

Bayesian optimization has emerged as a prominent methodology for optimizing expensive black-box functions by leveraging Gaussian process surrogates, which focus on capturing the global characteristics of the objective function. However, in numerous practical scenarios, the primary objective is not to construct an exhaustive global surrogate, but rather to quickly pinpoint the global optimum. Due to the aleatoric nature of the sequential optimization problem and its dependence on the quality of the surrogate model and the initial design, it is restrictive to assume that all observed samples contribute equally to the discovery of the optimum in this context. In this paper, we introduce Counterfactual Credit Guided Bayesian Optimization (CCGBO), a novel framework that explicitly quantifies the contribution of individual historical observations through counterfactual credit. By incorporating counterfactual credit into the acquisition function, our approach can selectively allocate resources in areas where optimal solutions are most likely to occur. We prove that CCGBO retains sublinear regret. Empirical evaluations on various synthetic and real-world benchmarks demonstrate that CCGBO consistently reduces simple regret and accelerates convergence to the global optimum.

Nian Ran, Zhongzheng Li, Yue Wang et al.

Multi-objective discrete optimization problems, such as molecular design, pose significant challenges due to their vast and unstructured combinatorial spaces. Traditional evolutionary algorithms often get trapped in local optima, while expert knowledge can provide crucial guidance for accelerating convergence. Large language models (LLMs) offer powerful priors and reasoning ability, making them natural optimizers when expert knowledge matters. However, closed-source LLMs, though strong in exploration, cannot update their parameters and thus cannot internalize experience. Conversely, smaller open models can be continually fine-tuned but lack broad knowledge and reasoning strength. We introduce Multi-LLM Collaborative Co-evolution (MCCE), a hybrid framework that unites a frozen closed-source LLM with a lightweight trainable model. The system maintains a trajectory memory of past search processes; the small model is progressively refined via reinforcement learning, with the two models jointly supporting and complementing each other in global exploration. Unlike model distillation, this process enhances the capabilities of both models through mutual inspiration. Experiments on multi-objective drug design benchmarks show that MCCE achieves state-of-the-art Pareto front quality and consistently outperforms baselines. These results highlight a new paradigm for enabling continual evolution in hybrid LLM systems, combining knowledge-driven exploration with experience-driven learning.

Rifny Rachman, Josh Tingey, Richard Allmendinger et al.

This study develops a generalised multi-objective, multi-echelon supply chain optimisation model with non-stationary markets based on a Markov decision process, incorporating economic, environmental, and social considerations. The model is evaluated using a multi-objective reinforcement learning (RL) method, benchmarked against an originally single-objective RL algorithm modified with weighted sum using predefined weights, and a multi-objective evolutionary algorithm (MOEA)-based approach. We conduct experiments on varying network complexities, mimicking typical real-world challenges using a customisable simulator. The model determines production and delivery quantities across supply chain routes to achieve near-optimal trade-offs between competing objectives, approximating Pareto front sets. The results demonstrate that the primary approach provides the most balanced trade-off between optimality, diversity, and density, further enhanced with a shared experience buffer that allows knowledge transfer among policies. In complex settings, it achieves up to 75\% higher hypervolume than the MOEA-based method and generates solutions that are approximately eleven times denser, signifying better robustness, than those produced by the modified single-objective RL method. Moreover, it ensures stable production and inventory levels while minimising demand loss.

Seyed Mahdi Shavarani, Mahmoud Golabi, Richard Allmendinger et al.

Evolutionary Multi-Objective Optimization Algorithms (EMOAs) are widely employed to tackle problems with multiple conflicting objectives. Recent research indicates that not all objectives are equally important to the decision-maker (DM). In the context of interactive EMOAs, preference information elicited from the DM during the optimization process can be leveraged to identify and discard irrelevant objectives, a crucial step when objective evaluations are computationally expensive. However, much of the existing literature fails to account for the dynamic nature of DM preferences, which can evolve throughout the decision-making process and affect the relevance of objectives. This study addresses this limitation by simulating dynamic shifts in DM preferences within a ranking-based interactive algorithm. Additionally, we propose methods to discard outdated or conflicting preferences when such shifts occur. Building on prior research, we also introduce a mechanism to safeguard relevant objectives that may become trapped in local or global optima due to the diminished correlation with the DM-provided rankings. Our experimental results demonstrate that the proposed methods effectively manage evolving preferences and significantly enhance the quality and desirability of the solutions produced by the algorithm.

Stefan Pricopie, Richard Allmendinger, Manuel Lopez-Ibanez et al.

We investigate modifications to Bayesian Optimization for a resource-constrained setting of sequential experimental design where changes to certain design variables of the search space incur a switching cost. This models the scenario where there is a trade-off between evaluating more while maintaining the same setup, or switching and restricting the number of possible evaluations due to the incurred cost. We adapt two process-constrained batch algorithms to this sequential problem formulation, and propose two new methods: one cost-aware and one cost-ignorant. We validate and compare the algorithms using a set of 7 scalable test functions in different dimensionalities and switching-cost settings for 30 total configurations. Our proposed cost-aware hyperparameter-free algorithm yields comparable results to tuned process-constrained algorithms in all settings we considered, suggesting some degree of robustness to varying landscape features and cost trade-offs. This method starts to outperform the other algorithms with increasing switching-cost. Our work broadens out from other recent Bayesian Optimization studies in resource-constrained settings that consider a batch setting only. While the contributions of this work are relevant to the general class of resource-constrained problems, they are particularly relevant to problems where adaptability to varying resource availability is of high importance

Mayowa Ayodele, Richard Allmendinger, Manuel López-Ibáñez et al.

Multi-objective optimisation problems involve finding solutions with varying trade-offs between multiple and often conflicting objectives. Ising machines are physical devices that aim to find the absolute or approximate ground states of an Ising model. To apply Ising machines to multi-objective problems, a weighted sum objective function is used to convert multi-objective into single-objective problems. However, deriving scalarisation weights that archives evenly distributed solutions across the Pareto front is not trivial. Previous work has shown that adaptive weights based on dichotomic search, and one based on averages of previously explored weights can explore the Pareto front quicker than uniformly generated weights. However, these adaptive methods have only been applied to bi-objective problems in the past. In this work, we extend the adaptive method based on averages in two ways: (i)~we extend the adaptive method of deriving scalarisation weights for problems with two or more objectives, and (ii)~we use an alternative measure of distance to improve performance. We compare the proposed method with existing ones and show that it leads to the best performance on multi-objective Unconstrained Binary Quadratic Programming (mUBQP) instances with 3 and 4 objectives and that it is competitive with the best one for instances with 2 objectives.

Claire Little, Mark Elliot, Richard Allmendinger et al.

Generative Adversarial Networks (GANs) are gaining increasing attention as a means for synthesising data. So far much of this work has been applied to use cases outside of the data confidentiality domain with a common application being the production of artificial images. Here we consider the potential application of GANs for the purpose of generating synthetic census microdata. We employ a battery of utility metrics and a disclosure risk metric (the Targeted Correct Attribution Probability) to compare the data produced by tabular GANs with those produced using orthodox data synthesis methods.

Chimdimma Noelyn Onah, Richard Allmendinger, Julia Handl et al.

The adoption of the Prospective Payment System (PPS) in the UK National Health Service (NHS) has led to the creation of patient groups called Health Resource Groups (HRG). HRGs aim to identify groups of clinically similar patients that share similar resource usage for reimbursement purposes. These groups are predominantly identified based on expert advice, with homogeneity checked using the length of stay (LOS). However, for complex patients such as those encountered in burn care, LOS is not a perfect proxy of resource usage, leading to incomplete homogeneity checks. To improve homogeneity in resource usage and severity, we propose a data-driven model and the inclusion of patient-level costing. We investigate whether a data-driven approach that considers additional measures of resource usage can lead to a more comprehensive model. In particular, a cost-sensitive decision tree model is adopted to identify features of importance and rules that allow for a focused segmentation on resource usage (LOS and patient-level cost) and clinical similarity (severity of burn). The proposed approach identified groups with increased homogeneity compared to the current HRG groups, allowing for a more equitable reimbursement of hospital care costs if adopted.

Richard Allmendinger, Andrzej Jaszkiewicz, Arnaud Liefooghe et al.

The difficulty of solving a multi-objective optimization problem is impacted by the number of objectives to be optimized. The presence of many objectives typically introduces a number of challenges that affect the choice/design of optimization algorithms. This paper investigates the drivers of these challenges from two angles: (i) the influence of the number of objectives on problem characteristics and (ii) the practical behavior of commonly used procedures and algorithms for coping with many objectives. In addition to reviewing various drivers, the paper makes theoretical contributions by quantifying some drivers and/or verifying these drivers empirically by carrying out experiments on multi-objective NK landscapes and other typical benchmarks. We then make use of our theoretical and empirical findings to derive practical recommendations to support algorithm design. Finally, we discuss remaining theoretical gaps and opportunities for future research in the area of multi- and many-objective optimization.

Richard Allmendinger, Joshua Knowles

Multiobjective optimization problems with heterogeneous objectives are defined as those that possess significantly different types of objective function components (not just incommensurable in units or scale). For example, in a heterogeneous problem the objective function components may differ in formal computational complexity, practical evaluation effort (time, costs, or resources), determinism (stochastic vs deterministic), or some combination of all three. A particularly challenging variety of heterogeneity may occur by the combination of a time-consuming laboratory-based objective with other objectives that are evaluated using faster computer-based calculations. Perhaps more commonly, all objectives may be evaluated computationally, but some may require a lengthy simulation process while others are computed from a relatively simple closed-form calculation. In this chapter, we motivate the need for more work on the topic of heterogeneous objectives (with reference to real-world examples), expand on a basic taxonomy of heterogeneity types, and review the state of the art in tackling these problems. We give special attention to heterogeneity in evaluation time (latency) as this requires sophisticated approaches. We also present original experimental work on estimating the amount of heterogeneity in evaluation time expected in many-objective problems, given reasonable assumptions, and survey related research threads that could contribute to this area in future.

Cameron Shand, Richard Allmendinger, Julia Handl et al.

Comprehensive benchmarking of clustering algorithms is rendered difficult by two key factors: (i)~the elusiveness of a unique mathematical definition of this unsupervised learning approach and (ii)~dependencies between the generating models or clustering criteria adopted by some clustering algorithms and indices for internal cluster validation. Consequently, there is no consensus regarding the best practice for rigorous benchmarking, and whether this is possible at all outside the context of a given application. Here, we argue that synthetic datasets must continue to play an important role in the evaluation of clustering algorithms, but that this necessitates constructing benchmarks that appropriately cover the diverse set of properties that impact clustering algorithm performance. Through our framework, HAWKS, we demonstrate the important role evolutionary algorithms play to support flexible generation of such benchmarks, allowing simple modification and extension. We illustrate two possible uses of our framework: (i)~the evolution of benchmark data consistent with a set of hand-derived properties and (ii)~the generation of datasets that tease out performance differences between a given pair of algorithms. Our work has implications for the design of clustering benchmarks that sufficiently challenge a broad range of algorithms, and for furthering insight into the strengths and weaknesses of specific approaches.

Youngmin Kim, Richard Allmendinger, Manuel López-Ibáñez

Safe learning and optimization deals with learning and optimization problems that avoid, as much as possible, the evaluation of non-safe input points, which are solutions, policies, or strategies that cause an irrecoverable loss (e.g., breakage of a machine or equipment, or life threat). Although a comprehensive survey of safe reinforcement learning algorithms was published in 2015, a number of new algorithms have been proposed thereafter, and related works in active learning and in optimization were not considered. This paper reviews those algorithms from a number of domains including reinforcement learning, Gaussian process regression and classification, evolutionary algorithms, and active learning. We provide the fundamental concepts on which the reviewed algorithms are based and a characterization of the individual algorithms. We conclude by explaining how the algorithms are connected and suggestions for future research.