Praneeth Vepakomma

Camera Culture
  • Research Assistant

Please visit https://praneeth.mit.edu/ for most up-to-date details around my research.

Bio: Praneeth Vepakomma is currently a PhD student. His main research page is https://praneeth.mit.edu.  His research focuses on developing algorithms for distributed scientific computation & ML under constraints of privacy, communication & efficiency.  He won the Meta (previously FB) 2022 Phd Research Fellowship in Applied Statistics. He has been selected as a SERC Scholar (Social and Ethical Responsibilities of Computing Scholar) by MIT’s Schwarzman College of Computing. His FedML work won a Best Paper Award at NeurIPS 2020-SpicyFL and his work on NoPeek-Infer won a Best Paper Runner Up Award at FG-2021. He was a TA & Mentor/Coach in 2019 & 2020 for the AI for Impact Courses recognized on MIT News. He was Interviewed in the book, 'Data Scientist: The Definitive Guide to Becoming a Data Scientist'.  His work on Split Learning featured in Technology Review.  He was previously a scientist at Apple (intern), Amazon, Motorola Solutions, PublicEngines, Corning (intern) an… View full description

Please visit https://praneeth.mit.edu/ for most up-to-date details around my research.

Bio: Praneeth Vepakomma is currently a PhD student. His main research page is https://praneeth.mit.edu.  His research focuses on developing algorithms for distributed scientific computation & ML under constraints of privacy, communication & efficiency.  He won the Meta (previously FB) 2022 Phd Research Fellowship in Applied Statistics. He has been selected as a SERC Scholar (Social and Ethical Responsibilities of Computing Scholar) by MIT’s Schwarzman College of Computing. His FedML work won a Best Paper Award at NeurIPS 2020-SpicyFL and his work on NoPeek-Infer won a Best Paper Runner Up Award at FG-2021. He was a TA & Mentor/Coach in 2019 & 2020 for the AI for Impact Courses recognized on MIT News. He was Interviewed in the book, 'Data Scientist: The Definitive Guide to Becoming a Data Scientist'.  His work on Split Learning featured in Technology Review.  He was previously a scientist at Apple (intern), Amazon, Motorola Solutions, PublicEngines, Corning (intern) and various startups, all of which were eventually acquired. He holds an MS in Mathematical & Applied Statistics from Rutgers University, New Brunswick.  

  1. The privacy-welfare trade-off: Effects of differential privacy on influence & welfare in social choice, Ibrahim Suat Evren,  Praneeth Vepakomma, Ramesh Raskar (2022)
  2. PrivateMail: Differentially private supervised manifold learning of deep features with privacy, @AAAI 2022, 36th AAAI Conference on Artificial Intelligence, (AAAI 2022) (PDF).
  3. 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
  4. Fedml: A research library and benchmark for federated machine learning (Baidu Best Paper Award at NeurIPS-SpicyFL 2020)  (PDF)
  5. NoPeek-Infer: Preventing face reconstruction attacks in distributed inference after on-premise training, (IEEE FG 2021) (PDF)  (Mukh Best Paper Runner Up Award)
  6. DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks  IEEE Computer Vison and Pattern Recogniton Conference (CVPR 2021) (PDF),
  7. Supervised Dimensionality Reduction via Distance Correlation Maximization, Electronic Journal of Statistics, volume 12 No.1, Pages 960--984, The Institute of Mathematical Statistics and the Bernoulli Society, 2018 (Journal) (PDF)   5.    Private measurement of nonlinear correlations between data hosted across multiple parties (PDF)      
  8. Advances and open problems in federated learning (PDF)( Foundations and Trends in Machine Learning -FnTML, 2020)
  9. AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learning, (PDF),  IEEE Global Communications Conference (IEEE GLOBECOM 2021)
  10. Parallel Quasi-concave set optimization: A new frontier that scales without needing submodularity (PDF)(SubsetML @ ICML)
  11. DAMS: Meta-estimation of private sketch data structures for differentially private COVID-19 contact tracing, (PRIML and PPML joint edition, NeurIPS-2020) (PDF)
  12. Splintering with distributions: A stochastic decoy scheme for private computation
  13. Assessing Disease Exposure Risk With Location Histories And Protecting Privacy: A Cryptographic Approach In Response To A Global Pandemic
  14. Split learning for health: Distributed deep learning without sharing raw patient data, (PDF) (Project page) (ICLR Workshop)
  15. Combinatorics of Distance Covariance: Inclusion-Minimal Maximizers of Quasi-Concave Set Functions for Diverse Variable Selection,  (Discrete Applied Mathematics, Journal)  (PDF)
  16. PPContactTracing: A privacy-preserving contact tracing protocol for covid-19 pandemic
  17. No Peek: A Survey of private distributed deep learning (PDF)
  18. Optimal bandwidth estimation for a fast manifold learning algorithm to detect circular structure in high-dimensional data (PDF)
  19. A Fast Algorithm for Manifold Learning by Posing it as a Symmetric Diagonally Dominant Linear System , Applied and Computational Harmonic Analysis (PDF)
  20. A-Wristocracy: Deep Learning on Wrist-worn Sensing for Recognition of User Complex Activities (PDF)(IEEE Body Sensor Networks)
  21. Apps gone rogue: Maintaining personal privacy in an epidemic
  22. ExpertMatcher: Automating ML Model Selection for Clients using Hidden Representations(2019 ICLR Workshop)
  23. "Scoring Practices for Remote Sensing of Land Mines", Mathematical Problems in Industry, MPI Workshop, Duke University.
  24. A Review of Homomorphic Encryption Libraries for Secure Computation (PDF)

Talks & Professional Service
Talks:
-Rutgers Mathematics dept. talk on Combinatorics of Distance Covariance, in Experimental Mathematics Seminar.
-Carnegie Mellon University, talk on Distributed & Privacy Preserving Computations, at See Below the Skin Expeditions.
-IBM Thomas J Watson Research Center, talk on Split Learning: A new resource efficient alternative for distributed ML, Workshop on Federated Learning and Analytics.
-INFORMS Annual Meeting, under Covid-19, Service Science Track on privacy preserving ML for health care: Private contact tracing and split learning.
-Tutorial at CVPR 2019 on distributed ML with federated learning and split learning.
-On Split Learning, a general talk at Datacouncil.ai
Reviewer: Journal of Machine Learning Research (JMLR), AISTATS conference, IJCAI conference, Transactions on Dependable and Secure Computing, IEEE Internet of Things Journal, IEEE Intelligent Systems, IEEE Transactions on Services Computing
Organizer:
Organized: ICML International Workshop on Federated Learning for User Privacy and Data Confidentiality, 2021 Keynote Speakers: Sebastian U. Stich, Nic Lane, Ramesh Raskar, Ameet Talwalkar, Filip Hanzely, Dimitris Papailiopoulos and Salman Avestimehr
Organized: ICLR Workshop on Distributed and Private Machine Learning (DPML, 2021).  Keynote Speakers: David Evans, Lalitha Sankar, Gauri Joshi & Graham Cormode.
CVPR Tutorial On Distributed Private Machine Learning for Computer Vision: Federated Learning, Split Learning and Beyond, 2019. Tutorial Speakers: Brendan McMahan, Jakub Konečný, Ramesh Raskar, Praneeth Vepakomma, Otkrist Gupta, Hassan Takabi
Organized: Workshop on Split Learning for Distributed Machine Learning (SLDML’21). Keynote Speakers: Peter Kairouz, OpenMined, Geeta Chauhan and Supriyo Chakraborty.​

Sampling of problems: A small sampling of problems that I work on includes a.) Private independence testing and private k-sample testing in statistics, b.) Bridging privacy with social choice theory, c.) Private mechanisms for training and inference in ML, d.) Privately estimating non-linear measures of statistical dependence between multiple parties and e.) Split learning.

Visit https://praneeth.mit.edu/ for most up-to-date details.