papers

Publications (23)

cs.LG2023

Diffusion-Augmented Neural Processes

Lorenzo Bonito, James Requeima, Aliaksandra Shysheya +1

Over the last few years, Neural Processes have become a useful modelling tool in many application areas, such as healthcare and climate sciences, in which data are scarce and predi…

stat.ML2020

Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes

James Requeima, Jonathan Gordon, John Bronskill +2

The goal of this paper is to design image classification systems that, after an initial multi-task training phase, can automatically adapt to new tasks encountered at test time. We…

stat.ML2024

Translation Equivariant Transformer Neural Processes

Matthew Ashman, Cristiana Diaconu, Junhyuck Kim +5

The effectiveness of neural processes (NPs) in modelling posterior prediction maps -- the mapping from data to posterior predictive distributions -- has significantly improved sinc…

cs.LG2025

A Meta-Learning Approach to Bayesian Causal Discovery

Anish Dhir, Matthew Ashman, James Requeima +1

Discovering a unique causal structure is difficult due to both inherent identifiability issues, and the consequences of finite data. As such, uncertainty over causal structures, su…

stat.ML2019

The Gaussian Process Autoregressive Regression Model (GPAR)

James Requeima, Will Tebbutt, Wessel Bruinsma +1

Multi-output regression models must exploit dependencies between outputs to maximise predictive performance. The application of Gaussian processes (GPs) to this setting typically y…

stat.ML2024

LLM Processes: Numerical Predictive Distributions Conditioned on Natural Language

James Requeima, John Bronskill, Dami Choi +2

Machine learning practitioners often face significant challenges in formally integrating their prior knowledge and beliefs into predictive models, limiting the potential for nuance…

q-fin.ST2015

Multi-scaling of wholesale electricity prices

Francesco Caravelli, James Requeima, Cozmin Ududec +3

We empirically analyze the most volatile component of the electricity price time series from two North-American wholesale electricity markets. We show that these time series exhibi…

cs.LG2023

Sim2Real for Environmental Neural Processes

Jonas Scholz, Tom R. Andersson, Anna Vaughan +2

Machine learning (ML)-based weather models have recently undergone rapid improvements. These models are typically trained on gridded reanalysis data from numerical data assimilatio…

cs.LG2026

Estimating Interventional Distributions with Uncertain Causal Graphs through Meta-Learning

Anish Dhir, Cristiana Diaconu, Valentinian Mihai Lungu +3

In scientific domains -- from biology to the social sciences -- many questions boil down to \textit{What effect will we observe if we intervene on a particular variable?} If the ca…

stat.ML2017

Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space

José Miguel Hernández-Lobato, James Requeima, Edward O. Pyzer-Knapp +1

Chemical space is so large that brute force searches for new interesting molecules are infeasible. High-throughput virtual screening via computer cluster simulations can speed up t…

physics.ao-ph2024

Aardvark weather: end-to-end data-driven weather forecasting

Anna Vaughan, Stratis Markou, Will Tebbutt +8

Weather forecasting is critical for a range of human activities including transportation, agriculture, industry, as well as the safety of the general public. Machine learning model…

stat.ML2022

Practical Conditional Neural Processes Via Tractable Dependent Predictions

Stratis Markou, James Requeima, Wessel P. Bruinsma +2

Conditional Neural Processes (CNPs; Garnelo et al., 2018a) are meta-learning models which leverage the flexibility of deep learning to produce well-calibrated predictions and natur…

cs.AI2024

AI for operational methane emitter monitoring from space

Anna Vaughan, Gonzalo Mateo-Garcia, Itziar Irakulis-Loitxate +8

Mitigating methane emissions is the fastest way to stop global warming in the short-term and buy humanity time to decarbonise. Despite the demonstrated ability of remote sensing in…

cs.LG2021

Efficient Gaussian Neural Processes for Regression

Stratis Markou, James Requeima, Wessel Bruinsma +1

Conditional Neural Processes (CNP; Garnelo et al., 2018) are an attractive family of meta-learning models which produce well-calibrated predictions, enable fast inference at test t…

cs.LG2026

Artificial intelligence for methane detection: from continuous monitoring to verified mitigation

Gonzalo Mateo-Garcia, Anna Allen, Itziar Irakulis-Loitxate +13

Methane is a potent greenhouse gas, responsible for roughly 30% of warming since pre-industrial times. A small number of large point sources account for a disproportionate share of…

stat.ML2025

JoLT: Joint Probabilistic Predictions on Tabular Data Using LLMs

Aliaksandra Shysheya, John Bronskill, James Requeima +4

We introduce a simple method for probabilistic predictions on tabular data based on Large Language Models (LLMs) called JoLT (Joint LLM Process for Tabular data). JoLT uses the in-…

stat.ML2020

Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes

Andrew Y. K. Foong, Wessel P. Bruinsma, Jonathan Gordon +3

Stationary stochastic processes (SPs) are a key component of many probabilistic models, such as those for off-the-grid spatio-temporal data. They enable the statistical symmetry of…

cs.LG2022

Challenges and Pitfalls of Bayesian Unlearning

Ambrish Rawat, James Requeima, Wessel Bruinsma +1

Machine unlearning refers to the task of removing a subset of training data, thereby removing its contributions to a trained model. Approximate unlearning are one class of methods…

stat.ML2023

Environmental Sensor Placement with Convolutional Gaussian Neural Processes

Tom R. Andersson, Wessel P. Bruinsma, Stratis Markou +8

Environmental sensors are crucial for monitoring weather conditions and the impacts of climate change. However, it is challenging to place sensors in a way that maximises the infor…

stat.ML2020

TaskNorm: Rethinking Batch Normalization for Meta-Learning

John Bronskill, Jonathan Gordon, James Requeima +2

Modern meta-learning approaches for image classification rely on increasingly deep networks to achieve state-of-the-art performance, making batch normalization an essential compone…

stat.ML2021

The Gaussian Neural Process

Wessel P. Bruinsma, James Requeima, Andrew Y. K. Foong +2

Neural Processes (NPs; Garnelo et al., 2018a,b) are a rich class of models for meta-learning that map data sets directly to predictive stochastic processes. We provide a rigorous a…

cs.LG2025

Context is Key: A Benchmark for Forecasting with Essential Textual Information

Andrew Robert Williams, Arjun Ashok, Étienne Marcotte +8

Forecasting is a critical task in decision-making across numerous domains. While historical numerical data provide a start, they fail to convey the complete context for reliable an…

stat.ML2020

Convolutional Conditional Neural Processes

Jonathan Gordon, Wessel P. Bruinsma, Andrew Y. K. Foong +3

We introduce the Convolutional Conditional Neural Process (ConvCNP), a new member of the Neural Process family that models translation equivariance in the data. Translation equivar…