51³Ô¹ÏÍø

Machine learning experts from across a range of departments at 51³Ô¹ÏÍø have successfully published papers as part of the 37th NeurIPS Conference.

A number of papers authored or co-authored by 51³Ô¹ÏÍø researchers from across the College have been accepted into the next edition of the - a prestigious machine learning and computational neuroscience conference.

Founded in 1987, the NeurIPS is now a multi-track interdisciplinary annual meeting that includes invited talks, demonstrations, symposia, and oral and poster presentations of refereed papers.

Alongside the conference is a professional exposition focusing on machine learning in practice, a series of tutorials, and topical workshops that provide a less formal setting for the exchange of ideas.

In particular this year, 51³Ô¹ÏÍø researcher Dr Dario Paccagnan in collaboration with Marco Campi and Simone Garatti from the Polytechnic University of Milan were accepted as a spotlight – a highly selective category. Their paper entitled ' focuses on the importance of generalization bounds in understanding learning processes and assessing model performance on new data. The researchers introduced a new framework, called Pick-to-Learn which helps to enhance the performance and reliability of machine learning models on unseen data.

In another paper, 51³Ô¹ÏÍø researchers Che Liu, Dr Sibo Cheng, Dr César Quilodrán Casas and Dr Rossella Arcucci from 51³Ô¹ÏÍø’s Data Science Institute and the Department of Earth Sciences and Engineering helped to create a new AI model to help computers understand medical data from different languages to reduce bias and improve their accuracy. Their paper, was created in partnership with The Ohio State University, Peking University, The Chinese University of Hong Kong and The Hong Kong University of Science and Technology and is explain more in this 51³Ô¹ÏÍø News Story.  

Finally in a paper by Dr Ciara Pike-Burke and Professor Aldo Faisal, , the 51³Ô¹ÏÍø team explored the benefits of hierarchical decomposition in improving the sample efficiency of algorithms in goal-conditioned hierarchical reinforcement learning. Their work is about how breaking down complex tasks into smaller, simpler sub-tasks can help algorithms learn more efficiently.

The list of accepted papers for NeurIPS2023 are below with 51³Ô¹ÏÍø academics linked:

., Pike-Burke, C. and Faisal, A. A., 2023. .

., Peach, R.L., . and Barahona, M., 2023. Interaction Measures, Partition Lattices and Kernel Tests for High-Order Interactions.

Wan, Z., Liu, C., Zhang, M., Fu, J., Wang, B., Cheng, S., Ma, L., Quilodrán-Casas, C. and Arcucci, R., 2023. .

Paccagnan, D., Campi, M. C. and Garatti, S., 2023.

., ., Lim, J. N., Li, Y., Vollmer, S. J. and Duncan, A. B., 2023. Energy Discrepancies: A Score-Independent Loss for Energy-Based Models. 

., Pike-Burke, C. and Rebeschini, P., 2023.

., Salazar, J. S. C., Feldmann, C., Walz, D., Sandfort, F., Mathea, M., Tsay, C. and Misener, R., 2023. . 

Swaminathan, S., Dedieu, A., Raju, R.V., Shanahan, M., Lazaro-Gredilla, M. and George, D., 2023. Schema-learning and rebinding as mechanisms of in-context learning and emergence. 

Issa, Z., Horvath, B., Lemercier, M. and Salvi, C., 2023. .

Ward, F.R., Everitt, T., . and Toni, F.,

Ekström Kelvinius, F., Georgiev, D., Petrov Toshev, A. and Gasteiger, J., 2023.

Veneziale, S., Coates, T. and Kasprzyk, A, 2023.

Kaissis, G., Ziller, A., Kolek, S. Riess, A. and Rueckert, D. 2023.