Rakshit Naidu

Rakshit (Rocket) Naidu

I am a first year PhD in Machine Learning (ML) student at ISyE, Georgia Tech. I am a recipient of the Thomas H. Johnson Fellowship award for the academic year of 2023-24.
I'm beyond fortunate to be co-advised by the awesome Professor Juba Ziani and Professor Kai Wang.
While my research interests hover around Responsible ML and Trustworthy AI, specifically tackling privacy and fairness issues in machine learning, I'm currently exploring how to register societal impact of AI applications through optimization.

Previously, I graduated with a Masters in Information Technology (MSIT-PE) degree from Carnegie Mellon University (CMU). During my time at CMU, I worked as a Research Assistant under Professor Hoda Heidari during Spring-Summer 2023 and I was also a Visiting Research Scholar at Syracuse University under Professor Ferdinando Fioretto during Summer 2022.

If you have any queries related to my work or a potential collaboration, please feel free to reach out to me!

In my free time, I play badminton and soccer . I used to represent CMU for Badminton (check out their Instagram page for more info: @cmubadminton!), now I serve as the "Social Media/PR Coordinator" at Georgia Tech Badminton Club (GTBC) Executive Body for the academic year 2024-25.
I also hold an Open Water scuba diving certification and I'm a (beginner) wakeboarder.

"Imagination is more important than knowledge. For knowledge is limited, whereas imagination embraces the entire world, stimulating progress, giving birth to evolution." ~Albert Einstein

Email / CV / Google Scholar / Twitter / Github / Old Github

I'm extremely fortunate to have collaborated with a very diverse set of professors namely (in no particular order)-- Ferdinando Fioretto (UVA/SyracuseU), Hoda Heidari (CMU), Franziska Boenisch (CISPA), Rayid Ghani (CMU), Kit Rodolfa (Stanford), Juba Ziani (Georgia Tech) and Emily Black (Barnard-Columbia/Stanford/CMU).

Additionally, I thank the following researchers who inspire me to continue doing what I do and I'm grateful to have collaborated, or rather still be collaborating, with them (in no particular order)-- Fatemehsadat Mireshghallah (UW/UCSD), Cuong Tran (UVA/SyracuseU), Krishna Acharya (Georgia Tech), Haofan Wang (Xiaohongshu/CMU), Aman Priyanshu (CMU/Manipal) and Supriti Vijay (Adobe/Manipal).

News

[Sept, 2023] We are organizing a NeurIPS'23 tutorial called Governance & Accountability for ML: Existing Tools, Ongoing Efforts, & Future Directions! Kudos to Emily and team :)
[Sept, 2023] I will serve as a Reviewer for AFCI-NeurIPS'23 and XAIA-NeurIPS'23. In other news, I also received a travel grant to attend EAAMO'23, see you soon Boston! :)
[July, 2023] Our recent paper Towards Operationalizing A pipeline-centric view of Fairness for ML has been accepted to ACM EAAMO'23 as an oral presentation! (18% acceptance rate)
[May, 2023] I will serve as a Reviewer and Ethics Reviewer for NeurIPS 2023. Additionally, I will serve on the Program Committee for GenLaw-ICML'23 and will also be a Reviewer for the workshop.
[April, 2023] I will start my PhD in ~~Computational Science and Engineering (CSE)~~ Machine Learning (ML) at ISyE, Georgia Tech this Fall!
[Oct, 2022] Our paper Pruning has a disparate impact on model accuracy has been accepted at NeurIPS 2022 as a Spotlight Lightning talk! It was also nominated for a best paper award, kudos to Cuong! =)

Selected Publications

For a full list of my publications, please visit my Google Scholar page.

Note: The convention in Theoretical CS is to list authors in alphabetical order by last name. (* indicates student author(s))

Personalized Differential Privacy for Ridge Regression
Krishna Acharya*, Franziska Boenisch, Rakshit Naidu*, Juba Ziani
Int'l Conference on Learning Representations (ICLR) 2024 Workshop on Privacy Regulation and Protection in Machine Learning. Preprint, 2024.

Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools
Emily Black, Rakshit Naidu, Rayid Ghani, Kit T. Rodolfa, Daniel E. Ho, Hoda Heidari
ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO), 2023 (archival)
Oral Presentation (18% acceptance rate)
NeurIPS'23 tutorial

Pruning has a disparate impact on model accuracy
Cuong Tran, Ferdinando Fioretto, Jung-Eun Kim, Rakshit Naidu
Neural Information Processing Systems (NeurIPS), 2022
Spotlight Lightning Talk (∼3% acceptance rate out of total 10,411 submissions in 2022)
(Nomination) Best Paper Award

FedPerf: A Practitioners' Guide to Performance of Federated Learning Algorithms
Ajinkya Mulay^*, Baye Gaspard^*, Rakshit Naidu^*, Santiago Gonzalez-Toral^*, Vineeth S^*, Tushar Semwal^*, Ayush Manish Agrawal
Proceedings of Machine Learning Research (PMLR), Volume 148, Pages 302-324, 2021,
Neural and Information Processing Systems (NeurIPS) 2020 Workshop on Pre-registration in Machine Learning.

Places I've visited:

I'm also an avid and a frequent traveler (I pretty much live a nomadic lifestyle!); already having visited 20+ countries.
Here, I keep a track of all the (new) places I've visited during my Masters/PhD :

Oranjestad, Aruba [Spring Break 2024]
San Diego, CA [Winter Break 2023]
New Orleans, LA [NeurIPS'23]
Boston, MA [EAAMO'23; WPTM-USENIX SOUPS'22]
Destin, FL [Fall Break 2023]
Asheville, NC / Blue Ridge Mountains [B'day + July 4th weekend]
Raleigh, NC [SaTML'23]
New Brunswick, NJ -- Rutgers University [Winter Break 2022]
San Juan, PR [Fall Break 2022]
Syracuse, NY [Summer Break 2022]
Niagara Falls, NY [Spring Break 2022]
Philadelphia, PA -- University of Pennsylvania (UPenn) [Winter Break 2021]

Thanks to Jon Barron for sharing the template/source code of this website!