Distinguished Lecture Series - Talk by Arthur Gretton (University College London)
We are pleased to announce our upcoming Distinguished Lecture Series talk by Arthur Gretton (University College London)! The talk will take place in person on December 4, in room UN32.101. Professor Gretton will also be available for meetings on December 4. If you are interested in scheduling a meeting, please email .
Arthur Gretton is a Professor with the Gatsby Computational Neuroscience Unit, director of the Centre for Computational Statistics and Machine Learning (CSML) at UCL; and a research scientist at Google Deepmind. His research interests include causal inference and representation learning, generative modeling, and nonparametric hypothesis testing. Arthur has served as associate editor at IEEE Transactions on Pattern Analysis and Machine Intelligence, an Action Editor for JMLR, a Senior Area Chair for NeurIPS (2018,2021) and ICML (2022), and a member of Royal Statistical Society Research Section Committee since January 2020. Arthur was program co-chair for AISTATS in 2016, tutorials co-chair for ICML 2018, workshops co-chair for ICML 2019, program co-chair for the Dali workshop in 2019, and co-organsier of the Machine Learning Summer School 2019 in London.
Title: Learning to Act in Noisy Contexts using Deep Proxy Learning
Learning to Act in Noisy Contexts using Deep Proxy Learning
We consider problem of evaluating the expected outcome of an action or policy, using off-policy observations, where the relevant context is noisy/anonymized. This scenario might arise due to privacy constraints, data bandwidth restrictions, or both. As an example, users might wish to determine the anticipated outcome of an exercise regime, with only an incomplete view available of their fitness levels (for instance, from journaling or wearables). We will employ the recently developed tool of proxy causal learning to address this problem. In brief, two noisy views of the context are used: one prior to the user action, and one subsequent to it, and influenced by the action. This pair of views will allow us to provably recover the average causal effect of an action under reasonable assumptions. As a key benefit of the proxy approach, we need never explicitly model or recover the hidden context. Our implementation employs learned neural net representations for both the action and context, allowing each to be complex and high dimensional (images, text). We demonstrate the deep proxy learning method in a setting where the action is an image, and show that we outperform an autoencoder-based alternative.
Date: December 4, 2024
Time: 11:30
Place: Universitätstraße 32.101, Campus Vaihingen of the University of Stuttgart.
Looking forward to seeing you all there! No registration necessary.