activity
20242026
collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2025

ONNX-Net: Towards Universal Representations and Instant Performance Prediction for Neural Architectures

Shiwen Qin, Alexander Auras, Shay B. Cohen +4

Neural architecture search (NAS) automates the design process of high-performing architectures, but remains bottlenecked by expensive performance evaluation. Most existing studies…

cs.LG2025

Transferrable Surrogates in Expressive Neural Architecture Search Spaces

Shiwen Qin, Gabriela Kadlecová, Martin Pilát +5

Neural architecture search (NAS) faces a challenge in balancing the exploration of expressive, broad search spaces that enable architectural innovation with the need for efficient…

cs.LG2025

Hyperparameter Selection in Continual Learning

Thomas L. Lee, Sigrid Passano Hellan, Linus Ericsson +2

In continual learning (CL) -- where a learner trains on a stream of data -- standard hyperparameter optimisation (HPO) cannot be applied, as a learner does not have access to all o…

cs.LG2024

einspace: Searching for Neural Architectures from Fundamental Operations

Linus Ericsson, Miguel Espinosa, Chenhongyi Yang +5

Neural architecture search (NAS) finds high performing networks for a given task. Yet the results of NAS are fairly prosaic; they did not e.g. create a shift from convolutional str…

cs.LG2024

Self-Supervised Disentanglement by Leveraging Structure in Data Augmentations

Cian Eastwood, Julius von Kügelgen, Linus Ericsson +4

Self-supervised representation learning often uses data augmentations to induce some invariance to "style" attributes of the data. However, with downstream tasks generally unknown…