seb

Sebastian Schmon,

DPhil (Oxon)

Welcome to my webpage. I am a machine learning researcher, statistician and AI enthusiast. Before moving to industry full-time, I worked as an Assistant Professor in Statistics at Durham University and a Research Scientist in the Research team at Improbable. My research interests lie at the intersection of statistics, machine learning and probability as well as applications to the sciences. My recent work involves, for instance, work on generative AI including large language models, embeddings and diffusion models. A list of publications can be found below. I obtained my DPhil (Oxford parlance for PhD) at the Department of Statistics of the University of Oxford under the supervision of Arnaud Doucet and George Deligiannidis.

As a consultant with several years of experience I have supported start-ups as well as large multinational companies to improve their analytical capabilites.

Workshop Papers

High Performance Simulation for Scalable Multi-Agent Reinforcement Learning

with Jordan Langham-Lopez and Patrick Cannon

AI4ABM Workshop, ICML 2022

Multi-agent reinforcement learning experiments and open-source training environments are typically limited in scale, supporting tens or sometimes up to hundreds of interacting agents. In this paper we demonstrate the use of Vogue, a high performance agent based model (ABM) framework. Vogue serves as a multi-agent training environment, supporting thousands to tens of thousands of interacting agents while maintaining high training throughput by running both the environment and reinforcement learning (RL) agents on the GPU. High performance multi-agent environments at this scale have the potential to enable the learning of robust and flexible policies for use in ABMs and simulations of complex systems. We demonstrate training performance with two newly developed, large scale multi-agent training environments. Moreover, we show that these environments can train shared RL policies on time-scales of minutes and hours.
@article{langham2022high,
title={High Performance Simulation for Scalable Multi-Agent Reinforcement Learning},
author={Langham-Lopez, Jordan and Schmon, Sebastian M and Cannon, Patrick},
journal={arXiv preprint arXiv:2207.03945},
year={2022}
}
						

Calibrating Agent-based Models to Microdata with Graph Neural Networks

with Joel Dyer and Patrick Cannon

AI4ABM Workshop, ICML 2022 (Best Paper Award)

Calibrating agent-based models (ABMs) to data is among the most fundamental requirements to ensure the model fulfils its desired purpose. In recent years, simulation-based inference methods have emerged as powerful tools for performing this task when the model likelihood function is intractable, as is often the case for ABMs. In some real-world use cases of ABMs, both the observed data and the ABM output consist of the agents' states and their interactions over time. In such cases, there is a tension between the desire to make full use of the rich information content of such granular data on the one hand, and the need to reduce the dimensionality of the data to prevent difficulties associated with high-dimensional learning tasks on the other. A possible resolution is to construct lower-dimensional time-series through the use of summary statistics describing the macrostate of the system at each time point. However, a poor choice of summary statistics can result in an unacceptable loss of information from the original dataset, dramatically reducing the quality of the resulting calibration. In this work, we instead propose to learn parameter posteriors associated with granular microdata directly using temporal graph neural networks. We will demonstrate that such an approach offers highly compelling inductive biases for Bayesian inference using the raw ABM microstates as output.
@article{dyer2022calibrating,
title={Calibrating Agent-based Models to Microdata with Graph Neural Networks},
author={Dyer, Joel and Cannon, Patrick and Farmer, J Doyne and Schmon, Sebastian M},
journal={arXiv preprint arXiv:2206.07570},
year={2022}
}
						

AnoDDPM: Anomaly Detection with Denoising Diffusion Probabilistic Models using Simplex Noise

with Julian Wyatt, Adam Leach and Chris G. Willcocks

NTIRE, New Trends in Image Restoration and Enhancement workshop, CVPR 2022

Generative models have been shown to provide a powerful mechanism for anomaly detection by learning to model healthy or normal reference data which can subsequently be used as a baseline for scoring anomalies. In this work we consider denoising diffusion probabilistic models (DDPMs) for unsupervised anomaly detection. DDPMs have superior mode coverage over generative adversarial networks (GANs) and higher sample quality than variational autoencoders (VAEs). However, this comes at the expense of poor scalability and increased sampling times due to the long Markov chain sequences required. We observe that within reconstruction-based anomaly detection a full-length Markov chain diffusion is not required. This leads us to develop a novel partial diffusion anomaly detection strategy that scales to high-resolution imagery, named AnoDDPM. A secondary problem is that Gaussian diffusion fails to capture larger anomalies; therefore we develop a multi-scale simplex noise diffusion process that gives control over the target anomaly size. AnoDDPM with simplex noise is shown to significantly outperform both f-AnoGAN and Gaussian diffusion for the tumorous dataset of 22 T1-weighted MRI scans (CCBS Edinburgh) qualitatively and quantitatively (improvement of +25.5\% Sørensen–Dice coefficient, +17.6\% IoU and +7.4\% AUC).
@InProceedings{Wyatt_2022_CVPR,     
author = {Wyatt, Julian and Leach, Adam and Schmon, Sebastian M. and Willcocks, Chris G.},     
title = {AnoDDPM: Anomaly Detection With Denoising Diffusion Probabilistic Models Using Simplex Noise},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2022},
pages = {650-656} 
}
						

Denoising diffusion probabilistic models on SO(3) for rotational alignment

with Adam Leach, Matteo T. Degiacomi and Chris G. Willcocks

Workshop on Geometrical and Topological Representation Learning, ICLR 2022

Probabilistic diffusion models are capable of modeling complex data distributions on high-dimensional Euclidean spaces for a range applications. However, many real world tasks involve more complex structures such as data distributions defined on manifolds which cannot be easily represented by diffusions on $\mathbb{R}^n$. This paper proposes denoising diffusion models for tasks involving 3D rotations leveraging diffusion processes on the Lie group $SO(3)$ in order to generate candidate solutions to rotational alignment tasks. The experimental results show the proposed $SO(3)$ diffusion process outperforms naïve approaches such as Euler angle diffusion in synthetic rotational distribution sampling and in a 3D object alignment task.

							
						

Implicit Priors for Knowledge Sharing in Bayesian Neural Networks

with Jack Fitzsimons and Stephen Roberts

4th Neurips workshop on Bayesian Deep Learning 2019

Bayesian approaches offer a robust statistical framework to introduce prior knowledge into learning procedures. However, the tasks introduced above can be challenging in practice since "information" gained by one network such as learned features can be difficult to encode into prior distributions over networks that do not share the same architecture or even the same output dimension. We introduce here a Bayesian viewpoint that centres around features and describe a set of prior distributions derived from the theory of Gaussian processes and deep kernel learning that facilitate a variety of deep learning tasks in a unified way. In particular, we will show that our approach is applicable to knowledge distillation, transfer learning and combining experts.
@Article{impprior,
author  = {Jack K Fitzsimons and Sebastian M Schmon and Stephen J Roberts},
title   = {Implicit Priors for Knowledge Sharing in Bayesian Neural Networks},
journal = {4th Neurips workshop on Bayesian Deep Learning},
year    = {2019},
}