Warwick Stats Conference - Scientific Programme 2026

Programme

22nd April - Day 1

22nd April
9.30 - 10.00	Registration and Kick-off
10.00 - 11.00	Plenary Talk Prof. Richard Samworth
11.00 - 12.00	Contributed Talks Session (x3)
12.00 - 13.00	Lunch
13.00 - 14.00	ECR led Discussion
14.00 - 14.30	Coffee Break
16.30 - 15.30	Plenary Talk Prof. Patrick Rebeschini
15.30 - 16.30	Contributed Talks Session (x3)
16.30 - 17.30	Poster session
18.30 - Late	Conference Dinner

23rd April - Day 2

23rd April
10.00 - 11.00	Plenary Talk
11.00 - 12.00	Contributed Talks Session (x3)
12.00 - 13.00	Lunch
13.00 - 14.00	Plenary Talk
14.00 - 14.30	Coffee Break
14.30 - 15.30	Plenary Talk
15.30 - 16.30	Contribute Talks Session (x3)
16.30 - 16.40	Short break
16.40 - 17.20	Contributed Talks Session (x2)
17.20 - 17.30	Closing Remarks & Farewell

All Talks and Contributed Sessions will take place in MS.05, Zeeman building.

The Poster Session will take place in the Statistics Atrium, MSB.

Plenary Speakers - Abstracts

Prof. Richard Samworth

Title: Learn the score

Abstract: Score estimation has recently emerged as a key modern statistical challenge, due to its pivotal role in generative modelling via diffusion models. Moreover, it is an essential ingredient in a new approach to linear regression via convex M-estimation, where the corresponding error densities are projected onto the log-concave class. I will outline the antitonic score matching framework that underpins this latter application, and explain its advantages over ordinary least squares, for both estimation and inference (e.g. prediction intervals). Motivated by both problems, I will then present new results on the minimax risk of score estimation over classes of log-concave densities.

Dr. Gonçalo dos Reis

Prof. Patrick Rebeschini

Prof. Rebecca Killick

Title: Regional and Global warming: A story of improving statistical literacy in climate science

Abstract: Global warming is always a hot topic and whatever side of the fence you sit on, you cannot deny the data that the climate is changing - regardless of attributing a cause to that. These changes have huge impacts on individual lives all over the world. In the UK we have had warmer summers and milder winters (at least in southern parts of the UK!) and more extreme weather events than earlier in the twentieth century. Most people have a storm, flooding or drought story, or know someone who has. In this talk, I will share some of my own stories about working with the data behind the headlines, mostly in temperature time series from across the globe. I will provide an introduction to the changepoint models I use to describe these temperature data and provide commentaries on working with environmental scientists and media engagement. From the statistical side, I am hoping that you will take away some insights into why changepoint models are useful, an intuition of (and some R packages for) how to apply these models to any data, and the key challenges you may come across in doing so. In littering my talk with anecdotes about interdisciplinary work, I am hoping to convey both the joys and realities of taking this approach to motivate those who haven't taken this path yet, whilst simultaneously building a shared connection with those who have.

Contributed Talks - Abstracts Posters - Abstracts