I am a research associate working with Arthur Gretton
at the Gatsby Computational Neuroscience Unit.
My research interest includes dictionary learning problems (structured sparse tasks, independent subspace analysis
and its extensions), kernel methods and information theory. I am also working on applications including blind signal separation, collaborative filtering,
natural language processing and facial expression recognition.
- Distribution Regression - the Set Kernel Heuristic is Consistent: invited talk at CSML Lunch Talk Series. [preprint, code; May 2, 2014 (soon)]
- Learning on Distributions: invited talk at Kernel methods for big data workshop, Lille. [PDF; Apr. 2, 2014]
- ITE (Information Theoretical Estimators) Toolbox: appeared in JMLR. [abstract, PDF; Mar. 6, 2014]
- Consistent Distribution Regression via Mean Embedding: invited talk at the University of Hertfordshire [PDF; Mar. 5, 2014]
- Consistent, Two-Stage Sampled Distribution Regression: available on arXiv. [abstract, PDF; Feb. 7, 2014]