12-13 September 2022, University of Bath
Statistical learning and deep learning techniques have been deployed in many parts of our lives, for example in search engines, online recommendation systems, and AI-assisted healthcare. An important question is how can we perform statistical learning to find general patterns from datasets without revealing data of individual participants? This question has become the key challenge that hinders further applications of statistical learning and deep learning in privacy-sensitive applications. Differential Privacy (DP) is a mathematical framework that can provide theoretical guarantees of privacy, while allowing us to achieve model utility and accuracy for specific applications. Mathematics has been the key for breakthroughs in developing statistical learning with DP. Recently, we have seen exciting developments in compressive learning and dynamical systems for designing and proving statistical learning algorithms with DP guarantees.
This workshop will bring together researchers and practitioners from statistical machine learning, deep learning, compressive sensing, dynamical systems and Bayesian neural networks to discuss this recent development and provide a snapshot of this interdisciplinary research topic to students, mathematicians, computer scientists and the wider community.
This workshop is organised by the Center for Mathematics and Algorithms for Data (MAD) at the University of Bath. It is sponsored by ART-AI and Maths4DL.
Monday 12 – Tuesday 13 September 2022
Clarice Poon (University of Bath), Antti Honkela (University of Helsinki), Antoine Chatalic (University of Genoa), Marco Avella Medina (Columbia University), Jordan Alexander Awan (Purdue University), Yves-Alexandre de Montjoye (Imperial College London), Alice Davis (Mayden), Coralia Cartis (Oxford), Christos Dimitrakakis (Université de Neuchâtel))
Abstracts of the talks
Cangxiong Chen, Tony Shardlow, Neill Campbell, Clarice Poon, Matt Nunes, Sandipan Roy, Teo Deveney