papers

Publications (39)

cs.LG2026

A Sobering Look at Tabular Data Generation via Probabilistic Circuits

Davide Scassola, Dylan Ponsford, Adrián Javaloy +4

Tabular data is more challenging to generate than text and images, due to its heterogeneous features and much lower sample sizes. On this task, diffusion-based models are the curre…

eess.SP2025

Is Limited Participant Diversity Impeding EEG-based Machine Learning?

Philipp Bomatter, Henry Gouk

The application of machine learning (ML) to electroencephalography (EEG) has great potential to advance both neuroscientific research and clinical applications. However, the genera…

cs.LG2021

Searching for Robustness: Loss Learning for Noisy Classification Tasks

Boyan Gao, Henry Gouk, Timothy M. Hospedales

We present a "learning to learn" approach for automatically constructing white-box classification loss functions that are robust to label noise in the training data. We parameteriz…

cs.GT2020

Altruistic Decision-Making for Autonomous Driving with Sparse Rewards

Jack Geary, Henry Gouk

In order to drive effectively, a driver must be aware of how they can expect other vehicles' behaviour to be affected by their decisions, and also how they are expected to behave b…

cs.LG2022

Attacking Adversarial Defences by Smoothing the Loss Landscape

Panagiotis Eustratiadis, Henry Gouk, Da Li +1

This paper investigates a family of methods for defending against adversarial attacks that owe part of their success to creating a noisy, discontinuous, or otherwise rugged loss la…

stat.ML2018

MaxGain: Regularisation of Neural Networks by Constraining Activation Magnitudes

Henry Gouk, Bernhard Pfahringer, Eibe Frank +1

Effective regularisation of neural networks is essential to combat overfitting due to the large number of parameters involved. We present an empirical analogue to the Lipschitz con…

cs.LG2023

Evaluating the Evaluators: Are Current Few-Shot Learning Benchmarks Fit for Purpose?

Luísa Shimabucoro, Timothy Hospedales, Henry Gouk

Numerous benchmarks for Few-Shot Learning have been proposed in the last decade. However all of these benchmarks focus on performance averaged over many tasks, and the question of…

stat.ML2021

Distance-Based Regularisation of Deep Networks for Fine-Tuning

Henry Gouk, Timothy M. Hospedales, Massimiliano Pontil

We investigate approaches to regularisation during fine-tuning of deep neural networks. First we provide a neural network generalisation bound based on Rademacher complexity that u…

stat.ML2020

Regularisation of Neural Networks by Enforcing Lipschitz Continuity

Henry Gouk, Eibe Frank, Bernhard Pfahringer +1

We investigate the effect of explicitly enforcing the Lipschitz continuity of neural networks with respect to their inputs. To this end, we provide a simple technique for computing…

cs.AI2026

The Reward Model Selection Crisis in Personalized Alignment

Fady Rezk, Yuangang Pan, Chuan-Sheng Foo +4

Personalized alignment from preference data has focused primarily on improving personal reward model (RM) accuracy, with the implicit assumption that better preference ranking tran…

cs.LG2026

The Signal in the Noise: OOD Detection Through Goodness-of-Fit Testing in Factorised Latent Spaces

Philipp Bomatter, Jack Geary, Henry Gouk

Deep generative models offer a natural foundation for out-of-distribution (OOD) detection, yet prior work has shown that their assigned likelihoods are notoriously unreliable indic…

cs.LG2025

Model Diffusion for Certifiable Few-shot Transfer Learning

Fady Rezk, Royson Lee, Henry Gouk +2

In contemporary deep learning, a prevalent and effective workflow for solving low-data problems is adapting powerful pre-trained foundation models (FMs) to new tasks via parameter-…

cs.LG2021

Self-Supervised Representation Learning: Introduction, Advances and Challenges

Linus Ericsson, Henry Gouk, Chen Change Loy +1

Self-supervised representation learning methods aim to provide powerful deep feature learning without the requirement of large annotated datasets, thus alleviating the annotation b…

cs.LG2021

Weight-Covariance Alignment for Adversarially Robust Neural Networks

Panagiotis Eustratiadis, Henry Gouk, Da Li +1

Stochastic Neural Networks (SNNs) that inject noise into their hidden layers have recently been shown to achieve strong robustness against adversarial attacks. However, existing SN…

stat.ML2024

On the Limitations of General Purpose Domain Generalisation Methods

Henry Gouk, Ondrej Bohdal, Da Li +1

We investigate the fundamental performance limitations of learning algorithms in several Domain Generalisation (DG) settings. Motivated by the difficulty with which previously prop…

cs.LG2025

Model Merging is Secretly Certifiable: Non-Vacuous Generalisation Bounds for Low-Shot Learning

Taehoon Kim, Henry Gouk, Minyoung Kim +1

Certifying the IID generalisation ability of deep networks is the first of many requirements for trusting AI in high-stakes applications from medicine to security. However, when in…

cs.CV2023

Meta Omnium: A Benchmark for General-Purpose Learning-to-Learn

Ondrej Bohdal, Yinbing Tian, Yongshuo Zong +5

Meta-learning and other approaches to few-shot learning are widely studied for image recognition, and are increasingly applied to other vision tasks such as pose estimation and den…

cs.LG2016

Fast Metric Learning For Deep Neural Networks

Henry Gouk, Bernhard Pfahringer, Michael Cree

Similarity metrics are a core component of many information retrieval and machine learning systems. In this work we propose a method capable of learning a similarity metric from da…

cs.AI2026

Benchmarking Open-Ended Multi-Agent Coordination in Language Agents

Kale-ab Abebe Tessera, Andras Szecsenyi, Cameron Barker +7

As language models are increasingly deployed as autonomous agents, they must coordinate with others over long horizons in open-ended interactive tasks. Yet existing evaluations rar…

cs.CV2023

Amortised Invariance Learning for Contrastive Self-Supervision

Ruchika Chavhan, Henry Gouk, Jan Stuehmer +3

Contrastive self-supervised learning methods famously produce high quality transferable representations by learning invariances to different data augmentations. Invariances establi…

cs.GT2026

Non-Linear Strategic Classification Made Practical

Jack Geary, Boyan Gao, Henry Gouk

Algorithmic developments in Strategic Classification have been mostly limited to linear classifiers in settings where the best response has a closed-form solution or can be easily…

cs.LG2025

Strategic Classification with Randomised Classifiers

Jack Geary, Henry Gouk

We consider the problem of strategic classification, where a learner must build a model to classify agents based on features that have been strategically modified. Previous work in…

cs.LG2024

Is Scaling Learned Optimizers Worth It? Evaluating The Value of VeLO's 4000 TPU Months

Fady Rezk, Antreas Antoniou, Henry Gouk +1

We analyze VeLO (versatile learned optimizer), the largest scale attempt to train a general purpose "foundational" optimizer to date. VeLO was trained on thousands of machine learn…

cs.CV2026

Test-Time Alignment of Text-to-Image Diffusion Models via Null-Text Embedding Optimisation

Taehoon Kim, Henry Gouk, Timothy Hospedales

Test-time alignment (TTA) aims to adapt models to specific rewards during inference. However, existing methods tend to either under-optimise or over-optimise (reward hack) the targ…

cs.GT2021

Resolving Conflict in Decision-Making for Autonomous Driving

Jack Geary, Subramanian Ramamoorthy, Henry Gouk

Recent work on decision making and planning for autonomous driving has made use of game theoretic methods to model interaction between agents. We demonstrate that methods based on…

cs.LG2021

Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition

Xueting Zhang, Debin Meng, Henry Gouk +1

Current state-of-the-art few-shot learners focus on developing effective training procedures for feature representations, before using simple, e.g. nearest centroid, classifiers. I…

cs.LG2022

Meta Mirror Descent: Optimiser Learning for Fast Convergence

Boyan Gao, Henry Gouk, Hae Beom Lee +1

Optimisers are an essential component for training machine learning models, and their design influences learning speed and generalisation. Several studies have attempted to learn m…

cs.CL2023

Effectiveness of Debiasing Techniques: An Indigenous Qualitative Analysis

Vithya Yogarajan, Gillian Dobbie, Henry Gouk

An indigenous perspective on the effectiveness of debiasing techniques for pre-trained language models (PLMs) is presented in this paper. The current techniques used to measure and…

cs.LG2019

Deep clustering with concrete k-means

Boyan Gao, Yongxin Yang, Henry Gouk +1

We address the problem of simultaneously learning a k-means clustering and deep feature representation from unlabelled data, which is of interest due to the potential of deep k-mea…

cs.LG2022

HyperInvariances: Amortizing Invariance Learning

Ruchika Chavhan, Henry Gouk, Jan Stühmer +1

Providing invariances in a given learning task conveys a key inductive bias that can lead to sample-efficient learning and good generalisation, if correctly specified. However, the…

stat.ML2019

Stochastic Gradient Trees

Henry Gouk, Bernhard Pfahringer, Eibe Frank

We present an algorithm for learning decision trees using stochastic gradient information as the source of supervision. In contrast to previous approaches to gradient-based tree le…

cs.LG2026

Magnitude Distance: A Geometric Measure of Dataset Similarity

Sahel Torkamani, Henry Gouk, Rik Sarkar

Quantifying the distance between datasets is a fundamental question in mathematics and machine learning. We propose \textit{magnitude distance}, a novel distance metric defined on…

cs.CV2022

Why Do Self-Supervised Models Transfer? Investigating the Impact of Invariance on Downstream Tasks

Linus Ericsson, Henry Gouk, Timothy M. Hospedales

Self-supervised learning is a powerful paradigm for representation learning on unlabelled images. A wealth of effective new methods based on instance matching rely on data-augmenta…

cs.LG2025

Computing Strategic Responses to Non-Linear Classifiers

Jack Geary, Boyan Gao, Henry Gouk

We consider the problem of strategic classification, where the act of deploying a classifier leads to strategic behaviour that induces a distribution shift on subsequent observatio…

cs.CV2021

How Well Do Self-Supervised Models Transfer?

Linus Ericsson, Henry Gouk, Timothy M. Hospedales

Self-supervised visual representation learning has seen huge progress recently, but no large scale evaluation has compared the many models now available. We evaluate the transfer p…

cs.AI2021

Active Altruism Learning and Information Sufficiency for Autonomous Driving

Jack Geary, Henry Gouk, Subramanian Ramamoorthy

Safe interaction between vehicles requires the ability to choose actions that reveal the preferences of the other vehicles. Since exploratory actions often do not directly contribu…

cs.LG2022

Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification

Adrian El Baz, Ihsan Ullah, Edesio Alcobaça +17

Although deep neural networks are capable of achieving performance superior to humans on various tasks, they are notorious for requiring large amounts of data and computing resourc…

cs.LG2026

Structured Inference with Large Language Gibbs

Sanghyeok Choi, Henry Gouk, Esmeralda S. Whitammer

The knowledge encoded in large language models (LLMs) can serve as a substrate for structured reasoning over variables describing a complex world, but accessing this knowledge in a…

cs.LG2020

Don't Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights

Linus Ericsson, Henry Gouk, Timothy M. Hospedales

In the absence of large labelled datasets, self-supervised learning techniques can boost performance by learning useful representations from unlabelled data, which is often more re…