Publications

* denotes equal contribution

• L. I. Midgley*, V. Stimper*, J. Antorán*, E. Mathieu*, B. Schölkopf and J.M. Hernández-Lobato. SE(3) Equivariant Augmented Coupling Flows. Spotlight at NeurIPS. 2023. [paper] [code]
• L. I. Midgley*, V. Stimper*, G. N. C Simm, B. Schölkopf and J.M. Hernández-Lobato. Flow Annealed Importance Sampling Bootstrap. Spotlight at ICLR. 2023. [paper] [code]
• C. Bonnet, D. Luo, D. Byrne, S. Surana, V. Coyette, P. Duckworth, L. I. Midgley, T. Kalloniatis, S. Abramowitz, C. N. Waters, A. P. Smit, N. Grinsztajn and U. A. Mbou Sob, O. Mahjoub and E. Tegegn, M. A. Mimouni, R. Boige, R. de Kock, D. Furelos-Blanco, V. Le, A. Pretorius, A. Laterre. Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX. InstaDeep 2023. [paper]. [code]
• C. Bonnet, L. I. Midgley, A. Laterre. Debiasing Meta-Gradient Reinforcement Learning by Learning the Outer Value Function. NeurIPS Meta-Learning Workshop. 2022. [paper]. [code]
• L. I. Midgley, V. Stimper, G. N. C Simm, and J.M. Hernández-Lobato. Bootstrap Your Flow. ELLIS Machine Learning for Molecule Discovery Workshop. 2021. [paper] [code]
• L. I. Midgley. Deep Reinforcement Learning for Process Synthesis. arxiv:2009.13265. 2020. [paper] [code]
• L. I. Midgley, M. Thomson. Reinforcement learning for chemical engineering process synthesis. 2019. [paper] [code]

Talks

• Flow Annealed Importance Sampling Bootstrap. Oxford Computational Statistics and Machine Learning Group (OxCSML) Seminar. 2023.
• Flow Annealed Importance Sampling Bootstrap. Oral (Spotlight Paper) at The International Conference for Learning Representations (ICLR). 2023
• Flow Annealed Importance Sampling Bootstrap. Graphs and Geometry Reading Group. 2023. [recording]
• Flow Annealed Importance Sampling Bootstrap. ELLIS Machine Learning for Molecule Discovery Workshop (oral presentation). 2022.
• Reinforcement learning for process synthesis. Computer-Aided Process Engineering Open Standards (CO-LaN) conference 2020. [recording]