14 papers
Latent Space Inference via Paired Autoencoders
Emma Hart, Bas Peters, Julianne Chung +1
This work describes a novel data-driven latent space inference framework built on paired autoencoders to handle observational inconsistencies when solving inverse problems. Our app…
Distributed Resource Selection for Self-Organising Cloud-Edge Systems
Quentin Renau, Amjad Ullah, Emma Hart
This paper presents a distributed resource selection mechanism for diverse cloud-edge environments, enabling dynamic and context-aware allocation of resources to meet the demands o…
Class Incremental Learning for Algorithm Selection
Mate Botond Nemeth, Emma Hart, Kevin Sim +1
Algorithm selection is commonly used to predict the best solver from a portfolio per per-instance. In many real scenarios, instances arrive in a stream: new instances become availa…
A Paired Autoencoder Framework for Inverse Problems via Bayes Risk Minimization
Emma Hart, Julianne Chung, Matthias Chung
In this work, we describe a new data-driven approach for inverse problems that exploits technologies from machine learning, in particular autoencoder network structures. We conside…
Algorithm Selection with Probing Trajectories: Benchmarking the Choice of Classifier Model
Quentin Renau, Emma Hart
Recent approaches to training algorithm selectors in the black-box optimisation domain have advocated for the use of training data that is algorithm-centric in order to encapsulate…
Beyond the Hype: Benchmarking LLM-Evolved Heuristics for Bin Packing
Kevin Sim, Quentin Renau, Emma Hart
Coupling Large Language Models (LLMs) with Evolutionary Algorithms has recently shown significant promise as a technique to design new heuristics that outperform existing methods,…
Stalling in Space: Attractor Analysis for any Algorithm
Sarah L. Thomson, Quentin Renau, Diederick Vermetten +3
Network-based representations of fitness landscapes have grown in popularity in the past decade; this is probably because of growing interest in explainability for optimisation alg…
Elucidating the Design Choice of Probability Paths in Flow Matching for Forecasting
Soon Hoe Lim, Yijin Wang, Annan Yu +4
Flow matching has recently emerged as a powerful paradigm for generative modeling and has been extended to probabilistic time series forecasting in latent spaces. However, the impa…
Identifying Easy Instances to Improve Efficiency of ML Pipelines for Algorithm-Selection
Quentin Renau, Emma Hart
Algorithm-selection (AS) methods are essential in order to obtain the best performance from a portfolio of solvers over large sets of instances. However, many AS methods rely on an…
Evaluating the Robustness of Deep-Learning Algorithm-Selection Models by Evolving Adversarial Instances
Emma Hart, Quentin Renau, Kevin Sim +1
Deep neural networks (DNN) are increasingly being used to perform algorithm-selection in combinatorial optimisation domains, particularly as they accommodate input representations…
Paired Autoencoders for Likelihood-free Estimation in Inverse Problems
Matthias Chung, Emma Hart, Julianne Chung +2
We consider the solution of nonlinear inverse problems where the forward problem is a discretization of a partial differential equation. Such problems are notoriously difficult to…
An Investigation of the Factors Influencing Evolutionary Dynamics in the Joint Evolution of Robot Body and Control
Léni K. Le Goff, Edgar Buchanan, Emma Hart
In evolutionary robotics, jointly optimising the design and the controller of robots is a challenging task due to the huge complexity of the solution space formed by the possible c…
Understanding fitness landscapes in morpho-evolution via local optima networks
Sarah L. Thomson, Léni K. Le Goff, Emma Hart +1
Morpho-evolution (ME) refers to the simultaneous optimisation of a robot's design and controller to maximise performance given a task and environment. Many genetic encodings have b…
On the Utility of Probing Trajectories for Algorithm-Selection
Quentin Renau, Emma Hart
Machine-learning approaches to algorithm-selection typically take data describing an instance as input. Input data can take the form of features derived from the instance descripti…