Arya Mazumdar
 |
HDSI Endowed Chair Professor in AI University of California San DiegoHalıcıoğlu School of Data Science and Computing Research InterestsI work on algorithmic and statistical aspects of machine learning, error correcting codes, optimization and signal processing. |
Updates
EnCORE Workshop: New Horizons on Adaptive Robustness.
ECE Distinguished Alumni Award, University of Maryland, College Park, 2025.
We are organizing an EnCORE Workshop on Theoretical Perspectives on LLMs. Thanks Google AI and NSF for the sponsorship.
EnCORE Workshop on Old Questions and New Directions in Theory of Clustering, Mar 4 - 7, 2024.
We are organizing EnCORE/IPAM Workshop on Computational vs Statistical Gaps in Learning and Optimization at UCLA Feb 26 - Mar 1, 2024. Please register to attend.
I am a Distinguished Lecturer of the IEEE Information Theory Society for 2023-2024.
NSF announced EnCORE Institute to be a TRIPODS Phase II Institute. UC San Diego News. Jacob School News. CSE News. HDSI News.
Mar 8, 2022: A Fortune Education article featuring my quotes on the growth of data science.
Foundational research in TILOS: UCSD News
The National Science Foundation announced our institute to be a National AI Institute, where I am a co-PI and co-leader of the Foundations research. For more information, see our website or read the UCSD News Story.
On April 9, 2021, we are organizing a Workshop on Communication Efficient Distributed Optimization. Please register (free) to attend and present a poster.
Some recent talks
On continual learning in neural networks at Simons Institute.
On generalized linear models at HOT-AI. A longer version at IFML.
On logistic regression at IMA. Shorter talk at Banff.
On 1-bit compressed sensing at EnCORE.
On combinatorics of 1-bit compressed sensing at Simons Institute.
On graph clustering in The Shannon channel. Another one at Bombay Information Theory Seminar.
Some older talks on coding theory
On locally repairable codes at IAS.
On storage capacity at Simons Institute.
Bio
I am a tenured full professor and the inaugural holder of the HDSI Chancellor's Endowed Chair in AI at the Halıcıoğlu Data Science Institute (HDSI), School of Data Science and Computing, and an affiliated professor in the Computer Science and Engineering and Electrical and Computer Engineering departments at UCSD. From 2015-2021, I was first an assistant, and then an associate professor of Computer Science at UMass with additional affiliations to Center for Data Science and Department of Mathematics and Statistics. During 2019-2020, I was also a senior scientist in Amazon in Berkeley, CA. My research is mainly supported by the NSF via multiple grants, including an NSF CAREER award. Before joining UMass, I was an assistant professor at University of Minnesota – Twin Cities (2013 – 2015). And even before that, I was a postdoctoral scholar at Signals, Information and Algorithms Lab led by Greg Wornell at MIT.
I received my PhD in 2011 from University of Maryland, College Park under the guidance of Alexander Barg. My thesis, Combinatorial Methods in Coding Theory, won a distinguished dissertation fellowship award in UMD, and also an ISIT Jack K Wolf paper award. While a graduate student, I spent summer of 2010 at IBM Almaden, San Jose, CA, and summer of 2008 at HP Labs, Palo Alto, CA doing internships. As of now, I am also serving as an Associate Editor of IEEE Transactions on Information Theory, an Action Editor for Transactions on Machine Learning Research, and as an Area Editor of Foundation and Trends in Communication and Information Theory, in addition to being a Distinguished Lecturer of the IEEE Information Theory Society.