- Camera Culture
Update: 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 and the FL-IJCAI'22 Best Student Paper Award for "Visual Transformer Meets CutMix for Split Learning", at the International Workshop on Trustworthy Federated Learning in Conjunction with IJCAI 2022 (FL-IJCAI'22). He was a TA & Mentor/Coach in 2019 & 2020 for the AI for Impact Courses recognized on MIT News and for Introduction to Statistical Data Analysis, EECS. 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.
- Private independence testing across two parties (PDF), Praneeth Vepakomma, Mohammad Mohammadi Amiri, Clément L. Canonne, Ramesh Raskar, Alex Pentland - Topic: Statistics, Hypothesis Testing, Differential Privacy, Independence Testing (2022)
- The privacy-welfare trade-off: Effects of differential privacy on influence & welfare in social choice, Ibrahim Suat Evren, Praneeth Vepakomma, Ramesh Raskar (2022)
- PrivateMail: Differentially private supervised manifold learning of deep features with privacy, @AAAI 2022, 36th AAAI Conference on Artificial Intelligence, (AAAI 2022) (PDF).
- 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
- Fedml: A research library and benchmark for federated machine learning (Baidu Best Paper Award at NeurIPS-SpicyFL 2020) (PDF).
- NoPeek-Infer: Preventing face reconstruction attacks in distributed inference after on-premise training, (IEEE FG 2021) (PDF) (Mukh Best Paper Runner Up Award)
- DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks IEEE Computer Vison and Pattern Recogniton Conference (CVPR 2021) (PDF),
- 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)
- Advances and open problems in federated learning (PDF), ( Foundations and Trends in Machine Learning -FnTML, 2020)
- AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learning, (PDF), IEEE Global Communications Conference (IEEE GLOBECOM 2021)
- Parallel Quasi-concave set optimization: A new frontier that scales without needing submodularity (PDF), (SubsetML @ ICML)
- DAMS: Meta-estimation of private sketch data structures for differentially private COVID-19 contact tracing, (PRIML and PPML joint edition, NeurIPS-2020) (PDF)
- Splintering with distributions: A stochastic decoy scheme for private computation
- Assessing Disease Exposure Risk With Location Histories And Protecting Privacy: A Cryptographic Approach In Response To A Global Pandemic
- Split learning for health: Distributed deep learning without sharing raw patient data, (PDF) (Project page) (ICLR Workshop)
- Combinatorics of Distance Covariance: Inclusion-Minimal Maximizers of Quasi-Concave Set Functions for Diverse Variable Selection , (Discrete Applied Mathematics, Journal) (PDF)
- PPContactTracing: A privacy-preserving contact tracing protocol for covid-19 pandemic
- No Peek: A Survey of private distributed deep learning (PDF)
- Optimal bandwidth estimation for a fast manifold learning algorithm to detect circular structure in high-dimensional data (PDF)
- A Fast Algorithm for Manifold Learning by Posing it as a Symmetric Diagonally Dominant Linear System , Applied and Computational Harmonic Analysis (PDF)
- A-Wristocracy: Deep Learning on Wrist-worn Sensing for Recognition of User Complex Activities (PDF), (IEEE Body Sensor Networks)
- Apps gone rogue: Maintaining personal privacy in an epidemic
- ExpertMatcher: Automating ML Model Selection for Clients using Hidden Representations, (2019 ICLR Workshop)
- "Scoring Practices for Remote Sensing of Land Mines", Mathematical Problems in Industry, MPI Workshop, Duke University.
- A Review of Homomorphic Encryption Libraries for Secure Computation (PDF)
Talks & Professional Service
Talks:
-Penn State University talk on Differential Privacy for Measuring Nonlinear Correlations between Sensitive Data at Multiple Parties. Talk video: Link: or Link: as part of Young Achievers Symposium series hosted by the Center for Socially Responsible Artificial Intelligence.
-PriSecML, Privacy and Security in ML Interest Group (London & the world): Private Measurement of Nonlinear Correlations in a Distributed Setting Link:
- RIKEN, AIP-Japan Link:
-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.