UCL ELLIS

UCL, a global leader in AI and machine learning, is a core component of the ELLIS network through its ELLIS Unit. ELLIS is a European AI network of excellence comprising Units within 30 research institutions. It focuses on fundamental science, technical innovation and societal impact. The ELLIS Unit at UCL spans across multiple departments (Gatsby Computational Neuroscience Unit, Department of Computer Science, Department of Statistical Science and Department of Electronic and Electrical Engineering).

“Some of the most effective learning algorithms are those that combine perspectives from many different models or parameters. This has always seemed a fitting metaphor for effective research. And now ELLIS will provide a new architecture to keep our real-life committee machine functioning --- reinforcing, deepening and enlarging the channels that connect us to colleagues throughout Europe At UCL we're excited to be a part of this movement to grow together. We look forward to sharing new collaborations, workshops, exchanges, joint studentships and more, and to the insight and breakthroughs that will undoubtedly follow. ”

Prof Maneesh Sahani
Director, Gatsby Computational Neuroscience Unit

“Advances in AI that benefit people and planet require global cooperation across disciplines and sectors. The ELLIS network is a vital part of that effort and UCL is proud to be a contributor. ”

Prof Geraint Rees
UCL Pro-Vice-Provost (AI)

News

London Meeting on Computational Statistics 2026

28 April 2026

The UCL Fundamentals of Statistical Machine Learning research group is organising the 'London Meeting on Computational Statistics 2026', which will take place on the 28th and 29th April at the London Mathematical Society. Topics covered will include Monte Carlo methods, variational inference, generative modelling, and simulation-based inference.

IMSS Annual Lecture by Dr Lester Mackey on Computational Statistics and Machine learning

27 April 2026

This year’s annual lecture of the UCL Institute for Mathematical and Statistical Sciences coincides with UCL's 200th Bicentennary and will focus on ''Computational Statistics and Machine Learning''. Members of the community are invited for an afternoon and evening of discussions on this topic, centered around a keynote talk by Dr. Lester Mackey (Microsoft Research New England and Stanford University).

UCL post-NeurIPS event

10 December 2025

UCL is hosting a post-NeurIPS event at the AI Centre to showcase outstanding research from UCL presented at NeurIPS. This includes an afternoon of talks, posters and drinks.

UCL NeuroAI Conference 2025

25 November 2025

The 2025 UCL NeuroAI Annual Conference aims to foster collaboration and knowledge exchange between researchers in neuroscience, AI, and machine learning by showcasing cutting-edge developments and facilitating interdisciplinary connections.

Workshop on 'Linking Geometry and Statistics - beyond a mere coincidence?'

23 September 2025

The UCL ELLIS unit is co-organising an event with the UCL Statistical Science department to celebrate the appointment of three new faculties working at the intersection of geometry and stats/ML. The event takes place at The Alan Turing Institute.

Events

Jump Trading/ELLIS CSML Seminar Series

RankSEG: A Consistent Ranking-based Framework for Segmentation

Speaker: Ben Dai

Event Date: 06 May 2026

Segmentation has emerged as a fundamental field of computer vision and natural language processing, which assigns a label to every pixel/feature to extract regions of interest from an image/text. To evaluate the performance of segmentation, the Dice and IoU metrics are used to measure the degree of overlap between the ground truth and the predicted segmentation. In this paper, we establish a theoretical foundation of segmentation with respect to the Dice/IoU metrics, including the Bayes rule and Dice-/IoU-calibration, analogous to classification-calibration or Fisher consistency in classification. We prove that the existing thresholding-based framework with most operating losses are not consistent with respect to the Dice/IoU metrics, and thus may lead to a suboptimal solution. To address this pitfall, we propose a novel consistent ranking-based framework, namely RankDice/RankIoU, inspired by plug-in rules of the Bayes segmentation rule. Three numerical algorithms with GPU parallel execution are developed to implement the proposed framework in large-scale and high-dimensional segmentation. We study statistical properties of the proposed framework. We show it is Dice-/IoU-calibrated, and its excess risk bounds and the rate of convergence are also provided. The numerical effectiveness of RankDice/mRankDice is demonstrated in various simulated examples and Fine-annotated CityScapes, Pascal VOC and Kvasir-SEG datasets with state-of-the-art deep learning architectures.

Pruning at Initialisation through the lens of Graphon Limits, or How to Prune Neural Networks in a Principled Way

Speaker: Long Tran-Thanh

Event Date: 13 May 2026

Sparse neural networks promise inference-time efficiency, yet training them effectively remains a fundamental challenge. Despite advances in pruning methods that create sparse architectures, understanding why some sparse structures are better trainable than others with the same level of sparsity remains poorly understood. Aiming to develop a systematic approach to this fundamental problem, we propose a novel theoretical framework based on the theory of graph limits, particularly graphons, that characterises sparse neural networks in the infinite-width regime. Our key insight is that connectivity patterns of sparse neural networks induced by pruning methods converge to specific graphons as networks' width tends to infinity, which encodes implicit structural biases of different pruning methods. Based on this, we derive a Graphon Neural Tangent Kernel (Graphon NTK) to study the training dynamics of sparse networks in the infinite width limit. Graphon NTK provides a general framework for the theoretical analysis of sparse networks. We empirically show that the spectral analysis of Graphon NTK correlates with observed training dynamics of sparse networks, explaining the varying convergence behaviours of different pruning methods. In addition, we also prove two fundamental theoretical results: (i) a Universal Approximation Theorem for sparse networks that depends only on the intrinsic dimension of active coordinate subspaces; and (ii) a Graphon-NTK generalisation bound demonstrating how the limit graphon modulates the kernel geometry to align with informative features. Overall, our framework provides theoretical insights into the impact of connectivity patterns on the trainability of various sparse network architectures. As such, it transforms the study of sparse neural networks from combinatorial graph problems into a rigorous framework of continuous operators, offering a new mechanism for analysing expressivity and generalisation in sparse neural networks.