Picture of Sarthak

Sarthak Chakraborty

Research Associate, Adobe India
Data-driven Systems, Insights and Experiences

About Me

I am Sarthak Chakraborty, currently working as a Research Associate at Big Data Experience Lab, Adobe Research, India. I am a part of the 'Data-driven Systems, Insights and Experiences' sub-group and will be collaborating with multiple excellent researchers to try to develop and design novel systems and algorithms pertaining to several diverse tasks.

My broad interests lies in the fields of Data-driven Systems, ML for Systems, Edge Computing, Distirbuted Systems and Machine Learning, in short, on the intersection of Machine Learning and Systems Design.

I graduated with a Dual Degree (B. Tech + M. Tech) in Computer Science and Engineering from the Indian Institute of Technology (IIT)Kharagpur. I have worked on the topic of "Cross-Chain Training of Learning Models via Blockchain Interoperability" as my Master's Thesis Project under Prof. Sandip Chakraborty. I have also completed my Bachelor's Thesis Project under the same professor on the topic of "Viewport Adaptive 360-degree Video Streaming". Furthermore, I have experience in fields of Federated Learning, Numerical Computations, Emotion Detection and Semi-Supervised Learning via several internships and projects.

Apart from my technical prowess, I am an avid reader (goodreads), sports enthusiast (especially football - P.S. a huge Barcelona and Messi fan), an adventure lover and a connoisseur of art and film-making. I like to read books and some of my favourite reads are 1984, To Kill a Mockingbird, Slaughterhouse-five and A Brief History of Time. In addition to that few of my favourite movies are The Shawshank Redemption, Parasite, Fight Club and The Godfather.

Latest News

13/07/21 Excited to start my first job as a Research Associate at Adobe, India.
15/01/21 My maiden paper on Viewport Adaptive 360 degree Video Streaming accepted at WWW!
25/11/20 New blog post comparing several methods of Thread Management and Thread Scheduling.
13/10/20 New blog post discussing Shared-Memory Multiprocessor systems and comparing various scheduling algorithms.

Publications

Lovish Chopra*, Sarthak Chakraborty*, Abhijit Mondal, Sandip Chakraborty
Proceedings of the Web Conference 2021 (WWW ’21), April 19–23, 2021, Ljubljana, Slovenia.

Internships

Big Data Experience Lab, Adobe India
Sunav Choudhary, Manoj Ghuhan
April 2020 - July 2020

Topic: Architecting Asynchronous Federated Learning
Research Areas: Federated Learning, Asynchronous FL algorithms, On-Client Training, Distributed Framework design

University of Waterloo (Mitacs Globalink Research Intern)
Hans de Sterck
May 2019 - July 2019

Topic: Advanced Optimization Methods for Machine Learning
Research Areas: CANDECOMP/PARAFAC Decomposition, Sparse Tensor Completion, Leverage Scores, Randomized Algorithm

IIT Kharagpur (collab. Shell India pvt. ltd.)
Swanand Khare
May 2018 - July 2018

Topic: Mean Time to Failure and Early Detection of Equipments (Predictive Maintenance)
Research Areas: Clustering Algorithms, EM Algorithm, Density Estimation, Gaussian Mixture Model

Teaching

CS43002: Database Management Systems (IIT Kharagpur) - Spring 2021
Teaching Assistant

course website

CS41001: Theory of Computation (IIT Kharagpur) - Fall 2020
Teaching Assistant

course website

Blogs

Thread Management and Thread Scheduling
15 Nov, 2020

Several concepts regarding thread management and their scheduling

Scheduling Algorithms for Shared-Memory Multi-Processor Systems
13 Oct, 2020

Inter and Intra process scheduling algorithms for SMP systems and their analysis

Understanding Deep Learning requires Re-Thinking Generalization
17 Aug, 2020

The following analysis is my interpretation of the ICLR 2017 paper “Understanding Deep Learning requires Re-Thinking Generalization”(arXiv link). This paper was awarded one of the three Best...

Contact

Email:

sarchakr <at> adobe <dot> com
<first_name>.<last_name> <at> gmail <dot> com
Additionally, you can also reach out to me via any of the social platforms like Facebook, LinkedIn or Twitter