I am an NSF postdoctoral fellow in the EECS department at Berkeley, working in the AMPLab with Mike Jordan. Previously, I was student at the Courant Institute (NYU) working with Mehryar Mohri. My interests include problems related to scalable and user-friendly machine learning, matrix factorization and computational genomics.
- MLI: An API for Distributed Machine
Learning (pdf, webpage)
E. Sparks, A. Talwalkar, V. Smith, J. Kottalam, X. Pan, J. Gonzalez, M. Franklin, M. I. Jordan, T. Kraska
International Conference on Data Mining (ICDM), 2013
- A Scalable Bootstrap for Massive Data (pdf)
A. Kleiner, A. Talwalkar, P. Sarkar, M.I. Jordan
Journal of the Royal Statistical Society, Series B (JRSS-B), 2013
- Large-scale SVD and Manifold Learning (pdf)
A. Talwalkar, S. Kumar, M. Mohri, H. Rowley
Journal of Machine Learning Research (JMLR), 2013
- Divide-and-Conquer Matrix Factorization (pdf, webpage)
L. Mackey, A. Talwalkar, M.I. Jordan
Neural Information Processing Systems (NIPS), 2011
- October 2013: We released SMaSH, our benchmarking toolkit for genomic variant calling algorithms.
- September 2013: MLlib, a distributed low-level machine learning library and a component of MLbase, was featured as part of the Spark 0.8.0 release.
- August 2013: We released the developer's preview of MLI, a user-friendly machine learning API and a part of MLbase, and presented a demo of it at AMPCamp.
- August 2012: Our textbook, Foundations of Machine Learning (MIT Press), has been published.
- September 2011: I am organizing a NIPS workshop on Sparse Representation and Low-rank Approximation.
- August 2011: I was awarded a three-year NSF OCI postdoctoral fellowship.
- March 2011: I am a recipient of the 2011 Janet Fabri Prize for best doctoral dissertation in NYU's Computer Science Department.
- September 2010: I am organizing a NIPS workshop on Low-rank Methods for Large-scale Machine Learning.