I am a research associate working with Arthur Gretton
at the Gatsby Unit.
My main research interests are information theory (ITE toolbox
), statistical machine learning, empirical processes, kernel methods.
I am also working on applications including remote sensing (sustainability), distribution regression, structured sparsity, independent
subspace analysis and its extensions, collaborative filtering.
- Paper (+):
TR: Learning Theory for Distribution Regression. [paper, code; Jan. 21, 2016]
- Accepted submission at Theory of Big Data Workshop [Dec. 4, 2015]:
- Optimal Uniform and Lp Rates for Random Fourier Features. [abstract, poster]
- 3 papers at NIPS-2015 [Sept. 4, 2015]:
- Optimal Rates for Random Fourier Features. [spotlight, poster, paper]
- Gradient-free Hamiltonian Monte Carlo with Efficient Kernel Exponential Families. [poster, paper, code]
- Bayesian Manifold Learning: The Locally Linear Latent Variable Model. [poster, paper, code]
- Invited talk (+):
- MASCOT-NUM 2016@ITM, INSA Toulouse [abstract, code; Mar. 23-25, 2016]
- Imperial College London: Department of Computing [Mar. 9, 2016]
- CMStatistics 2015 [abstract, slides, code; Dec. 12, 2015]
- Pennsylvania State University [slides; Dec. 4, 2015]
- Carnegie Mellon University: Statistical ML Reading Group [abstract, slides; Dec. 1, 2015], ML Lunch Seminar [abstract, slides, code; Nov. 30, 2015]
- Princeton University [abstract, slides, code; Nov. 26, 2015]
- University of Alberta [abstract, slides; Nov. 24, 2015]
- UC Berkeley [abstract, slides; Nov. 20, 2015]
- Else (+):