7 papers · 1 filter
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…
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…
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…
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…
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…