Praneeth Vepakomma

Employment

• Massachusetts Institute of Technology
  2018 - Present

Education

Education history is unavailable.

Projects & Funding

Projects & funding information is unavailable.

Publications (47)

• HSplitLoRA: A Heterogeneous Split Parameter-Efficient Fine-Tuning Framework for Large Language Models
  IEEE Transactions on Mobile Computing 2026 DOI: 10.1109/TMC.2026.3680521
  +Save
• Towards a Unified Framework for Split Learning
  2025 DOI: 10.1145/3721146.3721936
  +Save
• Mix2SFL: Two-Way Mixup for Scalable, Accurate, and Communication-Efficient Split Federated Learning
  IEEE Transactions on Big Data 2024 DOI: 10.1109/TBDATA.2023.3328424
  +Save
• Decouple-and-Sample: Protecting sensitive information in task agnostic data release
  arXiv 2022
  +Save
• Differentially Private Fréchet Mean on the Manifold of Symmetric Positive Definite (SPD) Matrices
  arXiv 2022 DOI: 10.48550/arXiv.2208.04245
  +Save
• LocFedMix-SL: Localize, Federate, and Mix for Improved Scalability, Convergence, and Latency in Split Learning
  WWW 2022 - Proceedings of the ACM Web Conference 2022 2022 DOI: 10.1145/3485447.3512153
  +Save
• Private independence testing across two parties
  arXiv 2022 DOI: 10.48550/arXiv.2207.03652
  +Save
• The privacy-welfare trade-off: Effects of differential privacy on influence & welfare in social choice
  arXiv 2022
  +Save
• Visual Transformer Meets CutMix for Improved Accuracy, Communication Efficiency, and Data Privacy in Split Learning
  arXiv 2022 DOI: 10.48550/arXiv.2207.00234
  +Save
• AdaSplit: Adaptive trade-offs for resource-constrained distributed deep learning
  arXiv 2021
  +Save
• Advances and open problems in federated learning
  Foundations and Trends in Machine Learning 2021 DOI: 10.1561/2200000083
  +Save
• AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learning
  2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings 2021 DOI: 10.1109/GLOBECOM46510.2021.9685232
  +Save
• AirMixML: Over-the-Air data mixup for inherently privacy-Preserving edge machine learning
  arXiv 2021
  +Save
• Differentially private supervised manifold learning with applications like private image retrieval
  arXiv 2021
  +Save
• DisCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks
  Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2021 DOI: 10.1109/CVPR46437.2021.01195
  +Save
• NoPeek-Infer: Preventing face reconstruction attacks in distributed inference after on-premise training
  Proceedings - 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2021 2021 DOI: 10.1109/FG52635.2021.9667085
  +Save
• Parallel quasi-concave set optimization: A new frontier that scales without needing submodularity
  arXiv 2021
  +Save
• Private measurement of nonlinear correlations between data hosted across multiple parties
  arXiv 2021
  +Save
• Server-side local gradient averaging and learning rate acceleration for scalable split learning
  arXiv 2021
  +Save
• Apps gone rogue: Maintaining personal privacy in an epidemic
  arXiv 2020
  +Save