I am a research associate working with Arthur Gretton
at the Gatsby Unit.
My main research interests are information theory (consistent estimators, distribution regression; ITE toolbox
), kernel methods and dictionary learning problems (structured sparse tasks, independent subspace analysis
and its extensions). I am also working on applications including remote sensing, blind signal separation, collaborative filtering,
natural language processing and facial expression recognition.
- Paper (+):
- Just-In-Time Kernel Regression for Expectation Propagation: accepted at ICML-2015) - Large-Scale Kernel Learning: Challenges and New Opportunities workshop [paper, code; May 15, 2015]
- Kernel-Based Just-In-Time Learning for Passing Expectation Propagation Messages: accepted at UAI-2015. [preprint on arXiv: abstract, paper; code; May 12, 2015]
- Data, Learning and Inference (DALI-2015) workshop: poster-1; poster-2 [Apr. 10-12, 2015].
- Two-stage Sampled Learning Theory on Distributions: accepted for oral presentation at AISTATS-2015. [6.11% oral acceptance rate, slides, paper; arXiv: abstract, paper; code; Jan. 11, 2015]
- Consistent Vector-valued Distribution Regression. [presented at UCL Workshop on the Theory of Big Data; abstract, slides, code; Jan. 8, 2015]
- TR: Learning Theory for Distribution Regression. [arXiv: abstract, paper; significant extension of abstract, paper; code; Dec. 6, 2014]
- Invited talk (+):
- CMStatistics 2015 [Dec. 12-14, 2015]
- University of Sheffield [Neil Lawrence's lab; Jun. 25-26, 2015]
- University of Warwick [CRiSM, event, abstract, code; May 29, 2015]
- University of Oxford [event, abstract, slides, code; May 1, 2015]
- University of Birmingham [event, abstract, slides, code; Jan. 26, 2015]
- MPI for Intelligent Systems [Bernhard Schölkopf's lab, abstract, slides, code; Jan. 14-18, 2015]
- Else (+):