Vipul Gupta
 |
PhD student, |
About me
I am a final-year graduate student in the department of Electrical Engineering and Computer Sciences (EECS) where I am working with Profs. Kannan Ramchandran, Thomas Courtade and Michael Mahoney. Before coming to Berkeley, I received Bachelors (with distinction) and Masters in the department of Electrical Engineering from the Indian Institute of Technology (IIT) Kanpur in 2015 and 2016, respectively. I've also been an Undergraduate researcher in summers’14 at Syracuse University and at EPFL in summers’15.
I am also a co-organizer of the BLISS Seminar, talks at which span information theory, machine learning, statistics, control, and optimization. Please send me an email if you are interested in giving a talk.
Feel free to contact me regarding anything that interests you on this site.
Research
My research lies at the intersection of
Machine Learning
Cloud Computing
Statistics
Information and Coding Theory
As a part of my Ph.D., I am happily working on problems that leverage ideas from statistics and information theory to speed-up distributed machine learning on inexpensive cloud-based services. My research is particularly motivated by problems with various practical applications. You can find a list of my publications here.
During my Ph.D., I have spent the summer and fall of 2020 with the ML infrastructure team at Facebook as a research engineer, where the aim was to develop and implement new techniques to improve the training efficiency of deep recommender models. During the summer of 2019, I was an intern at AI Research at Apple, Cupertino, where I worked on devising algorithms for accelerating distributed training of deep neural networks.