I am an assistant professor of Computer Science, affiliated assistant professor of Statistics, and Samueli Fellow at UCLA. I am also a technical advisor for Databricks. My interests include problems related to scalability and ease-of-use in the field of statistical machine learning, with applications in computational genomics. I was previously a postdoc in the AMPLab at Berkeley working with Michael Jordan. Before that, I was a student in the Courant Institute at NYU advised by Mehryar Mohri. Here is my CV, Google scholar page, and formal bio.
- A Novel Bandit-Based Approach to Hyperparameter Optimization
L. Li, K. Jamieson, G. DeSalvo, A. Rostamizadeh, A. Talwalkar
- MLlib: Machine Learning in Apache Spark (pdf)
X. Meng, J. Bradley, B. Yuvaz, E. Sparks, S. Venkataraman, D. Liu, J. Freeman, D. Tsai, M. Amde, S. Owen, D. Xin, R. Xin, M. Franklin, R. Zadeh, M. Zaharia, A. Talwalkar
- Distributed Matrix Completion and Robust Factorization (pdf)
L. Mackey, A. Talwalkar, M. I. Jordan
- MLbase: A Distributed Machine Learning System (pdf)
T. Kraska, A. Talwalkar, J. Duchi, R. Griffith, M.J. Franklin, M.I. Jordan
- A Scalable Bootstrap for Massive Data (pdf)
A. Kleiner, A. Talwalkar, P. Sarkar, M.I. Jordan
- Foundations of Machine Learning (web)
M. Mohri, A. Rostamizadeh, A. Talwalkar
MIT Press, 2012
- Large-Scale Manifold Learning (pdf)
A. Talwalkar, S. Kumar, H. Rowley
- Nov 2016: Congrats to Lisha Li for winning best student presentation at the Socal ML Symposium for our work on Hyperband! Also, congrats to Hang Qi on being runner-up for best real-world application for our work on Paleo!
- July 2016: Anthony Joseph and I are finalists for the edX Teaching Prize! Relatedly, I'm launching an updated version of my MOOC this month.
- June 2016: Check out these blog posts (one, two) that nicely summarize some of our recent work on hyperparameter optimization.
- Oct 2015: Thank you Amazon, Bloomberg, and Google for generous research awards.
- Jan 2015: I taught a three day course at the Berkeley Institute of Data Science (BIDS) on Distributed Analytics and Machine Learning with Apache Spark.
- Nov 2014: I'm teaching a MOOC next Spring. Check out the edX site to learn more and/or to register (it's free!): Scalable Machine Learning.
- Sept 2014: I am co-organizing a NIPS workshop on Distributed Machine Learning and Matrix Computations.
- June 2014: I am joining UCLA's Computer Science Department as an assistant professor. For the next year, I will be working at Databricks.
- Oct 2013: We released SMaSH, our benchmarking toolkit for genomic variant calling algorithms.
- Sept 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.
- Aug 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.
- Aug 2012: Our textbook, Foundations of Machine Learning (MIT Press), has been published.
- Sept 2011: I am co-organizing a NIPS workshop on Sparse Representation and Low-rank Approximation.
- Aug 2011: I was awarded a three-year NSF OCI postdoctoral fellowship.
- Mar 2011: I am a recipient of the 2011 Janet Fabri Prize for best doctoral dissertation in NYU's Computer Science Department.
- Sept 2010: I am co-organizing a NIPS workshop on Low-rank Methods for Large-scale Machine Learning.