Biography

Joel is a senior postdoctoral researcher developing methodology and tooling for simulation models. He completed his DPhil in computational statistics and machine learning at the University of Oxford’s Mathematical Institute and Institute for New Economic Thinking under the supervision of Prof. J. Doyne Farmer, where his research focus was on likelihood-free parameter inference methods for simulation models. Previously, Joel has worked as a Research Scientist at Improbable, and has held visiting research positions at The Alan Turing Institute and University of Bristol through The Alan Turing Institute’s Enrichment Scheme.

Recent Publications

Sept 2024
INET Working Paper
No. 2024-06 - Forecasting Macroeconomic Dynamics using a Calibrated Data-Driven Agent-based Model
Samuel Wiese ,  Jagoda Kaszowska-Mojsa ,  Joel Dyer ,  Jose Moran ,  Marco Pangallo ,  François Lafond ,  John Muellbauer ,  Anisoara Calinescu ,  J. Doyne Farmer
Sept 2024
Journal
Approximate Bayesian Computation with Path Signatures
in Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence
Joel Dyer ,  Patrick Cannon ,  Sebastian M Schmon
Feb 2024
Journal
Black-box Bayesian inference for agent-based models
in Journal of Economic Dynamics and Control
Joel Dyer ,  Patrick Cannon ,  J. Doyne Farmer ,  Sebastian Schmon
Jan 2024
Journal
Interventionally consistent surrogates for agent-based simulators
in NeurIPS 2024
Joel Dyer ,  Nicholas Bishop ,  Yorgos Felekis ,  Fabio Massimo Zennaro ,  Anisoara Calinescu ,  Theodoros Damoulas ,  Michael Wooldridge
Jan 2024
Journal
Population synthesis as scenario generation for simulation-based planning under uncertainty
in Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2024)
Joel Dyer ,  Arnau Quera-Bofarull ,  Nicholas Bishop ,  J. Doyne Farmer ,  Anisoara Calinescu ,  Michael Wooldridge
Nov 2023
Journal
Gradient-assisted calibration for financial agent-based models
in Proceedings of the Fourth ACM International Conference on AI in Finance (ICAIF '23)
Joel Dyer ,  Arnau Quera-Bofarull ,  Ayush Chopra ,  J. Doyne Farmer ,  Anisoara Calinescu ,  Michael Wooldridge
Oct 2023
Journal
Black-box inference for differentiable simulators
in Journal of Open Source Software
Arnau Quera-Bofarull ,  Joel Dyer ,  Anisoara Calinescu ,  J. Doyne Farmer ,  Michael Wooldridge
May 2023
Journal
Bayesian calibration of differentiable agent-based models
in ICLR 2023 Workshop on AI for Agent-Based Modelling
Arnau Quera-Bofarull ,  Ayush Chopra ,  Anisoara Calinescu ,  Michael Wooldridge ,  Joel Dyer
Feb 2023
Working Paper
Approximate Bayesian Computation with Path Signatures
Joel Dyer ,  Patrick Cannon ,  Sebastian M Schmon
Jul 2022
Journal
Calibrating Agent-based Models to Microdata with Graph Neural Networks
in ICML 2022 Workshop on AI for Agent-based Modelling
Joel Dyer ,  Patrick Cannon ,  J. Doyne Farmer ,  Sebastian M Schmon
Feb 2022
Journal
Amortised likelihood-free inference for expensive time-series simulators with signatured ratio estimation
in 25th International Conference on Artificial Intelligence and Statistics (AISTATS)
Joel Dyer ,  Patrick Cannon ,  Sebastian M Schmon
Dec 2020
Journal
Public risk perception and emotion on Twitter during the Covid-19 pandemic
in Applied Network Science
Joel Dyer ,  Blas Kolic

Recent Events

13 Jun 24
@12:00

INET Oxford Summer Research Meeting 2024

The event is open to all INET Oxford researchers, staff, visitors, and associate members

In Person Event
INET RGB
23 Nov 23
@14:00
Joel Dyer
12 May 22
@14:00
Joel Dyer
04 Nov 21
@15:00
Joel Dyer

Programme Teams