Statistical Learning and Differential Privacy
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 machine learning 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.
The workshop schedule can be found here.
We will have a workshop dinner on Monday the 12th.
If you would like to participate, please registrate here.
How to get here?
We have information on travelling to the city of Bath and getting to the university’s Claverton Down campus by bus.
Marco Avella Medina (Columbia University, slides), Jordan Alexander Awan* (Purdue University, slides), Coralia Cartis (Oxford, slides), Antoine Chatalic (University of Genoa, slides), Cangxiong Chen (University of Bath), Alice Davis (Mayden), Christos Dimitrakakis* (Université de Neuchâtel, slides), Antti Honkela (University of Helsinki, slides), Yves-Alexandre de Montjoye (Imperial College London), Clarice Poon (University of Bath, slides)
*: This speaker will present virtually.
Abstracts of the talks
Please find the abstracts of the talks, including a short bio of each speaker here.
Cangxiong Chen, Tony Shardlow, Neill Campbell, Clarice Poon, Matt Nunes, Sandipan Roy, Teo Deveney
Christina Squire, Helena Lake