Welcome

Who/Where: PhD Student at Massachusetts Institute of Technology (on 2023 faculty job market):  
I previously spent some time at Apple (intern), Meta (intern), Amazon (AWS), Motorola Solutions and several startups such as TripleBlind and PublicEngines after completing my MS in Mathematical & Applied Statistics at Dept. of Statistics, Rutgers, New Brunswick. I lived/worked in Visakhapatnam, New Brunswick, New York City, Atlanta, Salt Lake City and Seattle before moving to Boston. I won a Meta (previously FB) 2022 Phd Research Fellowship. If you are looking for an official Bio, scroll all the way to the end. Twitter: @ proneat. Am advised by professors Ramesh Raskar & Alex "Sandy" Pentland
 
Current Research: My focus is on algorithms for distributed scientific computation in statistics & machine learning under constraints of privacy, communication & computational efficiency. My work is inspired by foundations of non-asymptotic statistics, randomized algorithms, learning augmented algorithms, combinatorics, and at times just by systems design. Am also part of a dynamic See Below the Skin expeditions.
 
Teaching:
(Spring 2022) TA for 6.401 (6.481) Introduction to Statistical Data Analysis, EECSby Devavrat ShahUndergrad & Grad course with problem-sets, weekly recitations by TA's, mid-term, final & office hours.
(Spring 2020) TA: MAS.664 AI for Impact Towards Solving Societal-Scale Problems, by my advisor Ramesh Raskar.
(Fall 2022) Taking the semester long Kaufman Teaching Certificate Program for those interested in academic careers and to further develop skills to support teaching.
Awards/News:

Selected works:

welcome requests for high-level insight, in-depth one/two-way feedback, collaboration and invited talks (check contact me). 

34. Private mechanisms for nonlinear correlations and independence testing with energy statistics (PDF), Praneeth Vepakomma, Mohammad Mohammadi Amiri, Subha Nawer Pushpita, Clément Canonne, Ramesh Raskar, Alex Pentland - Topic: Statistics, Independence Testing, Private Correlations, Differential Privacy (2022)

 

33. Differentially private Fréchet Mean on the Manifold of Symmetric Positive Definite (SPD) Matrices (PDF), Saiteja Utpala, Praneeth Vepakomma, Nina Miolane - Topic: Geometric Statistics, Differential Privacy, Differential Geometry (2022)

 

32. Differentially private CutMix for Split Learning with Vision Transformer, Seungeun Oh, Sihun Baek, Hyelin Nam, Seong-Lyun Kim, Praneeth Vepakomma, Ramesh Raskar, Mehdi Bennis - Topic: Split Learning, Differential Privacy (2022)

 

31. Formal Privacy Guarantees for Neural Network queries by estimating local Lipschitz constant (PDF), @Workshop on Formal Verification of Machine Learning-ICML, Abhishek Singh, Praneeth Vepakomma, Vivek Sharma, Ramesh Raskar - Topic: Differential Privacy, Modified Propose-Test-Release, Lipschitz Constant (2022)

 

30. The privacy-welfare trade-off: Effects of differential privacy on influence & welfare in social choice (PDF), Ibrahim Suat Evren, Praneeth Vepakomma, Ramesh Raskar - Topic: Fourier analysis of Boolean functions, Differential Privacy, Social choice theory (2022)

 

29. Decouple-and-Sample: Protecting sensitive information in task agnostic data release, (PDF) @ECCV 2022, European Conference on Computer VisionAbhishek Singh, Ethan Garza, Ayush Chopra, Praneeth Vepakomma, Vivek Sharma, Ramesh Raskar, -Topic: Synthetic data, Differential privacy (only on partial component of latent space-a double-edged sword), Decorrelation (2022)

 

28. Private measurement of nonlinear correlations between data hosted across multiple partiesPraneeth Vepakomma, Subha Nawer Pushpita, Ramesh Raskar (PDF) -Topic: Statistics, Differential Privacy (2021)

 

 

27. PrivateMail: Differentially private supervised manifold learning of deep features with privacy, @AAAI 2022, 36th AAAI Conference on  Artificial Intelligence, (AAAI 2022) (Oral), Praneeth Vepakomma, Julia Balla, Ramesh Raskar (PDF) -Topic: Differential Privacy, Privacy Preserving ML, On-device ML (2022)

 

26. LocFedMix-SL: Localize, Federate, and Mix for Improved Scalability, Convergence, and Latency in Split Learning, @ WWW 2022 : International World Wide Web Conference/The Web Conf(WWW 2022)Seungeun Oh, Jihong Park, Praneeth Vepakomma, Sihun Baek, Ramesh Raskar, Mehdi Bennis and Seong-Lyun Kim (PDF) Distributed ML, Split Learning  

 

 

25. An Automated Framework for Distributed Deep Learning--A Tool Demo, Gharib Gharibi, Ravi Patel, Anissa Khan, Babak Poorebrahim Gilkalaye, Praneeth Vepakomma, Ramesh Raskar, Steve Penrod, Greg Storm, Riddhiman Das Topic: Demo, @ICDCS 2022, 42nd IEEE International Conference on Distributed Computing Systems (2022)

 

 

24. DISCO: Dynamic and invariant sensitive channel obfuscation for deep neural networks@ CVPR 2021, IEEE Computer Vison and Pattern Recogniton Conference, A.Singh, A.Chopra,V.Sharma, E.Garza, E.Zhang, P.Vepakomma, R.Raskar-Main Paper: (PDF) on  -Topic: Preventing reconstruction attacks, Distributed Inference (2021)

 

23. (New!) NoPeek-Infer: Preventing face reconstruction attacks in distributed inference after on-premise training, @FG 2021, IEEE International Conference on Automatic Face and Gesture Recognition (IEEE FG 2021) (Oral) , Praneeth Vepakomma, Abhishek Singh, Emily Zhang, Otkrist Gupta, Ramesh Raskar, (PDF)  -Topic: Reconstruction attacks, ML (2021) (Mukh Best Paper Runner Up Award at IEEE FG 2021)

 

 

22. Supervised Dimensionality Reduction via Maximization of Distance Correlation, @Electronic Journal of Statistics(Journal),  P.Vepakomma, C. Tonde and A.Elgammal, (PDF) -Topic: Statistics, Optimization, ML 

 

 

21. FedML: A research library and benchmark for federated machine learning C He, S Li, J So, M Zhang, H Wang, X Wang, P Vepakomma, A Singh, R Raskar (PDF)  (Best Paper Award at NeurIPS 2020-SpicyFL), -Topic: Federated ML/Distributed ML/Systems (2021)

 

 

20. AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learning, @ GLOBECOM 2021, IEEE Global Communications Conference, Yusuke Koda, Jihong Park, Mehdi Bennis, Praneeth Vepakomma, Ramesh Raskar  (PDF)– Topic: Differential Privacy, ML, Wireless, Analog communication, Over-the-air, Early proof of concept (Early PoC) 

 

 

19. AdaSplit: Adaptive trade-offs for resource-constrained distributed deep learning, Ayush Chopra, Surya Kant Sahu, Abhishek Singh, Abhinav Java, Praneeth Vepakomma, Vivek Sharma, Ramesh Raskar (PDF) -Topic: Distributed ML/Split Learning (2022)

 

18. Diverse data selection via combinatorial quasi-concavity of distance covariance: A polynomial time global minimax algorithm, (PDF)Praneeth Vepakomma, Yulia Kempner, @Discrete Applied Mathematics (Journal)-Topic: Statistics, optimization (2019)

 

17. Advances and open problems in federated learning, (PDF)  @Foundationa & Trends in Machine Learning, Vol 14, Issue 1–2 with 58 authors from 25 institutions, (Journal), -Topic: Federated ML/Distributed ML (2021)

 

16. Parallel Quasi-concave set optimization: A new frontier that scales without needing submodularity, Praneeth Vepakomma, Yulia Kempner, Ramesh Raskar, SubSetML: Subset Selection in Machine Learning: From Theory to Practice @ ICML 2021 Workshop (PDF) -Topic: Distributed ML, Combinatorial statistics, Combinatorial optimization (2021)

 

15. D.A.M.S: Meta-estimators of private sketch data structures for differentially private COVID-19 contact tracing(PDF), P.Vepakomma, S.N. Pushpita, R. Raskar, PRIML AND PPML JOINT EDITION @ NeurIPS-2020 Workshop, -Topic: Statistics, Differential Privacy, Privacy Preserving ML  (2020)

 

 

14. Split learning for health: Distributed deep learning without sharing raw patient data(PDF) Praneeth Vepakomma, Otkrist

Gupta, Tristan Swedish, Ramesh Raskar https://arxiv.org/pdf/1812.00564.pdf, Project page: https://splitlearning.github.io/,

@ICLR 2019 Workshop on AI for social good. -Topic: Federated ML/Distributed ML, Split Learning (2018)

 

 

13. A Fast Algorithm for Manifold Learning by Posing it as a Symmetric Diagonally Dominant Linear System, (PDF)Praneeth

Vepakomma & Ahmed Elgammal, Applied and Computational Harmonic Analysis, (Journal) Topic: ML

 

12. Server-Side Local Gradient Averaging and Learning Rate Acceleration for Scalable Split Learning, @ FL-AAAI 2022 Workshop, Shraman Pal, Mansi Uniyal, Jihong Park, Praneeth Vepakomma, Ramesh Raskar, Mehdi Bennis, Moongu Jeon, Jinho Choi (PDF) -Topic: Distributed ML, Split Learning (2022)

 

11. Splintering with distributions: A stochastic decoy scheme for private computation, P Vepakomma, J Balla, R Raskar

arXiv preprint arXiv:2007.02719 -Topic: Privacy Preserving ML

 

10. SplitNN-driven Vertical Partitioning(PDF) I Ceballos, V Sharma, E Mugica, A Singh, A Roman, P Vepakomma, arXiv preprint

arXiv:2008.0413, -Topic: Federated ML/Distributed ML

 

9. Privacy in Deep Learning: A Survey(PDF) F Mirshghallah, M Taram, P Vepakomma, A Singh, R Raskar-Topic: Privacy Preserving ML

 

8. PPContactTracing: A Privacy-Preserving Contact Tracing Protocol for COVID-19 Pandemic, (PDF) P Singh, A Singh, G

Cojocaru, P Vepakomma, R Raskar arXiv preprint arXiv:2008.06648-Topic: Cryptographic Tools

 

7. Assessing Disease Exposure Risk with Location Histories and Protecting Privacy: A Cryptographic Approach in

Response to A Global Pandemic, (PDF) A Berke, M Bakker, P Vepakomma, R Raskar, K Larson, AS Pentland-Topic: Cryptographic Tools

 

6. ExpertMatcher: Automating ML Model Selection for Clients using Hidden Representations, (PDF) Vivek Sharma, Praneeth

Vepakomma, Tristan Swedish, Ken Chang, Jayashree Kalpathy-Cramer, and Ramesh Raskar, NeurIPS Workshop on

Robust AI in Financial Services: Data, Fairness, Explainability, Trustworthiness, and Privacy, -Topic: Federated ML/Distributed ML

 

5. A Review of Homomorphic Encryption Libraries for Secure Computation, (PDF) Sai Sri Sathya, Praneeth Vepakomma,

Ramesh Raskar, Ranjan Ramachandra, and Santanu Bhattacharya,  -Topic: Cryptographic Tools

 

4. Optimal bandwidth estimation for a fast manifold learning algorithm to detect circular structure in highdimensional

data, (PDF) Praneeth Vepakomma and Susovan Pal, Topic: ML

 

3. Scoring practices for remote sensing of land mines (PDF), Praneeth Vepakomma, Adel Al Weshah, Aaron Bardall, Valeria

Barra, Dean Duffy, Hamza Ghadgali, Sarafa Iyaniwura , Hangjie Ji, Qingxia Li, Richard Moore, Kenneth Morton, Ryan

Pellico, Christina Selby, Razvan Stefanescu, Melissa Strait, Zhe Wang, Andres Vargas, Mathematical Problems in

Industry, Duke University-Department of Mathematics, -Topic: ML

 

2. A-Wristocracy: Deep Learning on Wrist-worn Sensing for Recognition of User Complex Activities, (PDF)Praneeth

Vepakomma, Debraj De, Sajal K. Das & Shekhar Bhansali at IEEE Body Sensor Networks Conference, at MIT Media Lab,

Cambridge, IEEE-BSN 2015, -Topic: ML, Wearables, Hardware/Software Integration

 

1. Split Learning on FPGA’s and FPIA’s: The first Field Programmable Imaging Arrays, Hannah Whisnant, Praneeth

Vepakomma, Ramesh Raskar, -Topic: Federated ML, On-Device ML, Hardware/Software Integration

 
...more on Google Scholar.

Organizer:

Community Service: 

  • Volunteered and conducted interactive demos for students at Shiloh Point Elementary School, Cumming, GA (Atlanta) for the Family Science Night.
  • Service at homeless shelter in Salt Lake City, UT with PublicEngines. Helped with sorting of donation material (non-monetary). 

Bio: Praneeth Vepakomma is currently a PhD student at MIT and has industrial experience in Meta, Apple, Amazon, Motorola Solutions, Corning and several startups. His research focuses on developing algorithms for distributed computation in statistics & machine learning under constraints of privacy, & efficiency. He won the Meta PhD research fellowship in Applied Statistics, two SERC Scholarships (Social and Ethical Responsibilities of Computing) from MIT's Schwarzman college of computing, a Best Student Paper Award at FL-IJCAI, a Baidu Best Paper Award at NeurIPS-SpicyFL and a Best Paper Runner Up Award at FG-2021. His technical work is inspired by foundations of non-asymptotic statistics, randomized algorithms, learning augmented algorithms, combinatorics, and at times just by systems design. He was Interviewed in the book, 'Data Scientist: The Definitive Guide to Becoming a Data Scientist' and has organized several workshops at ICLR, ICML, IJCAI, CVPR and NeurIPS.