【AI Workshop】Data-Efficient Machine Learning @ Imperial College London

On 12th Dec 2018, the topic of this event is data-efficient machine learning.

Speaker’s Bio:

Cheng Zhang is a researcher at the Machine Intelligence and Perception group at Microsoft Research Cambridge. Before joining Microsoft, she was at the Statistical Machine Learning group, at Disney Research Pittsburgh, located at Carnegie Mellon University. She has received her PhD at the Department of Robotics, Perception and Learning (RPL/ former CVAP), KTH Royal Institute of Technology Stockholm. She is interested in both machine learning theory, including variational inference, deep generative models and causality, as well as various machine learning applications with social impact.

Talk Abstract:

Making decisions using machine learning requires information concerning data to the task at hand. In many real-life applications, the datasets available are often not ideal, where missing data is typical. In this talk, I will present machine learning methods that can utilize datasets with missing data entries and efficiently acquire information in a cost-saving manner. In particular, I will mainly focus on two projects. The first one is the project EDDI for Efficient Dynamic Discovery of high-value Information. In EDDI, we propose a novel partial variational autoencoder (Partial VAE), to efficiently handle missing data over varying subsets of known information. Based on Bayesian experimental design, EDDI combines this Partial VAE with an acquisition function that maximizes expected information gain on a set of target variables. EDDI is efficient and demonstrates that dynamic discovery of high-value information is possible. Secondly, I will present work on active mini-batch sampling using point processes. This simultaneously balances the dataset with selection bias and reduces the variance for stochastic gradient methods. I will conclude the talk with my general research schedule and the research interest in machine intelligence and perception group in Microsoft Research, Cambridge.