Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Praneeth Vepakomma

Praneeth Vepakomma

Private measurement of nonlinear correlations between data hosted across multiple parties


Oct 19, 2021
Praneeth Vepakomma, Subha Nawer Pushpita, Ramesh Raskar

Figure 1 for Private measurement of nonlinear correlations between data hosted across multiple parties
Figure 2 for Private measurement of nonlinear correlations between data hosted across multiple parties
Figure 3 for Private measurement of nonlinear correlations between data hosted across multiple parties
Figure 4 for Private measurement of nonlinear correlations between data hosted across multiple parties

  Access Paper or Ask Questions

Parallel Quasi-concave set optimization: A new frontier that scales without needing submodularity


Aug 19, 2021
Praneeth Vepakomma, Yulia Kempner, Ramesh Raskar

Figure 1 for Parallel Quasi-concave set optimization: A new frontier that scales without needing submodularity
Figure 2 for Parallel Quasi-concave set optimization: A new frontier that scales without needing submodularity
Figure 3 for Parallel Quasi-concave set optimization: A new frontier that scales without needing submodularity
Figure 4 for Parallel Quasi-concave set optimization: A new frontier that scales without needing submodularity
* SubSetML: Subset Selection in Machine Learning: From Theory to Practice 
  Access Paper or Ask Questions

AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learning


May 02, 2021
Yusuke Koda, Jihong Park, Mehdi Bennis, Praneeth Vepakomma, Ramesh Raskar

Figure 1 for AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learning
Figure 2 for AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learning
Figure 3 for AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learning
Figure 4 for AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learning
* 6 pages, 6 figures 
  Access Paper or Ask Questions

Differentially Private Supervised Manifold Learning with Applications like Private Image Retrieval


Feb 22, 2021
Praneeth Vepakomma, Julia Balla, Ramesh Raskar

Figure 1 for Differentially Private Supervised Manifold Learning with Applications like Private Image Retrieval
Figure 2 for Differentially Private Supervised Manifold Learning with Applications like Private Image Retrieval
Figure 3 for Differentially Private Supervised Manifold Learning with Applications like Private Image Retrieval
Figure 4 for Differentially Private Supervised Manifold Learning with Applications like Private Image Retrieval
* 22 pages 
  Access Paper or Ask Questions

DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks


Dec 20, 2020
Abhishek Singh, Ayush Chopra, Vivek Sharma, Ethan Garza, Emily Zhang, Praneeth Vepakomma, Ramesh Raskar

Figure 1 for DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks
Figure 2 for DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks
Figure 3 for DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks
Figure 4 for DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks
* Extended version of NeurIPS PPML 2020 workshop paper 
  Access Paper or Ask Questions

NoPeek: Information leakage reduction to share activations in distributed deep learning


Aug 20, 2020
Praneeth Vepakomma, Abhishek Singh, Otkrist Gupta, Ramesh Raskar

Figure 1 for NoPeek: Information leakage reduction to share activations in distributed deep learning
Figure 2 for NoPeek: Information leakage reduction to share activations in distributed deep learning
Figure 3 for NoPeek: Information leakage reduction to share activations in distributed deep learning
Figure 4 for NoPeek: Information leakage reduction to share activations in distributed deep learning

  Access Paper or Ask Questions

SplitNN-driven Vertical Partitioning


Aug 07, 2020
Iker Ceballos, Vivek Sharma, Eduardo Mugica, Abhishek Singh, Alberto Roman, Praneeth Vepakomma, Ramesh Raskar

Figure 1 for SplitNN-driven Vertical Partitioning
Figure 2 for SplitNN-driven Vertical Partitioning
Figure 3 for SplitNN-driven Vertical Partitioning
Figure 4 for SplitNN-driven Vertical Partitioning
* First version, please provide feedback 
  Access Paper or Ask Questions

FedML: A Research Library and Benchmark for Federated Machine Learning


Jul 27, 2020
Chaoyang He, Songze Li, Jinhyun So, Mi Zhang, Hongyi Wang, Xiaoyang Wang, Praneeth Vepakomma, Abhishek Singh, Hang Qiu, Li Shen, Peilin Zhao, Yan Kang, Yang Liu, Ramesh Raskar, Qiang Yang, Murali Annavaram, Salman Avestimehr

Figure 1 for FedML: A Research Library and Benchmark for Federated Machine Learning
Figure 2 for FedML: A Research Library and Benchmark for Federated Machine Learning
Figure 3 for FedML: A Research Library and Benchmark for Federated Machine Learning
Figure 4 for FedML: A Research Library and Benchmark for Federated Machine Learning
* We maintain the source code, documents, and user community at https://fedml.ai 
  Access Paper or Ask Questions

Splintering with distributions: A stochastic decoy scheme for private computation


Jul 07, 2020
Praneeth Vepakomma, Julia Balla, Ramesh Raskar

Figure 1 for Splintering with distributions: A stochastic decoy scheme for private computation
Figure 2 for Splintering with distributions: A stochastic decoy scheme for private computation
Figure 3 for Splintering with distributions: A stochastic decoy scheme for private computation
Figure 4 for Splintering with distributions: A stochastic decoy scheme for private computation
* 28 pages, 6 figures 
  Access Paper or Ask Questions

Privacy in Deep Learning: A Survey


May 09, 2020
Fatemehsadat Mireshghallah, Mohammadkazem Taram, Praneeth Vepakomma, Abhishek Singh, Ramesh Raskar, Hadi Esmaeilzadeh

Figure 1 for Privacy in Deep Learning: A Survey
Figure 2 for Privacy in Deep Learning: A Survey
Figure 3 for Privacy in Deep Learning: A Survey
Figure 4 for Privacy in Deep Learning: A Survey

  Access Paper or Ask Questions

Split Learning for collaborative deep learning in healthcare


Dec 27, 2019
Maarten G. Poirot, Praneeth Vepakomma, Ken Chang, Jayashree Kalpathy-Cramer, Rajiv Gupta, Ramesh Raskar

Figure 1 for Split Learning for collaborative deep learning in healthcare
Figure 2 for Split Learning for collaborative deep learning in healthcare
Figure 3 for Split Learning for collaborative deep learning in healthcare
* Workshop paper: 8 pages, 2 figures, 1 table 
  Access Paper or Ask Questions

Advances and Open Problems in Federated Learning


Dec 10, 2019
Peter Kairouz, H. Brendan McMahan, Brendan Avent, AurΓ©lien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Keith Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael G. L. D'Oliveira, Salim El Rouayheb, David Evans, Josh Gardner, Zachary Garrett, AdriΓ  GascΓ³n, Badih Ghazi, Phillip B. Gibbons, Marco Gruteser, Zaid Harchaoui, Chaoyang He, Lie He, Zhouyuan Huo, Ben Hutchinson, Justin Hsu, Martin Jaggi, Tara Javidi, Gauri Joshi, Mikhail Khodak, Jakub KonečnΓ½, Aleksandra Korolova, Farinaz Koushanfar, Sanmi Koyejo, TancrΓ¨de Lepoint, Yang Liu, Prateek Mittal, Mehryar Mohri, Richard Nock, Ayfer Γ–zgΓΌr, Rasmus Pagh, Mariana Raykova, Hang Qi, Daniel Ramage, Ramesh Raskar, Dawn Song, Weikang Song, Sebastian U. Stich, Ziteng Sun, Ananda Theertha Suresh, Florian TramΓ¨r, Praneeth Vepakomma, Jianyu Wang, Li Xiong, Zheng Xu, Qiang Yang, Felix X. Yu, Han Yu, Sen Zhao

Figure 1 for Advances and Open Problems in Federated Learning
Figure 2 for Advances and Open Problems in Federated Learning
Figure 3 for Advances and Open Problems in Federated Learning
Figure 4 for Advances and Open Problems in Federated Learning

  Access Paper or Ask Questions

ExpertMatcher: Automating ML Model Selection for Clients using Hidden Representations


Oct 09, 2019
Vivek Sharma, Praneeth Vepakomma, Tristan Swedish, Ken Chang, Jayashree Kalpathy-Cramer, Ramesh Raskar

Figure 1 for ExpertMatcher: Automating ML Model Selection for Clients using Hidden Representations
Figure 2 for ExpertMatcher: Automating ML Model Selection for Clients using Hidden Representations
Figure 3 for ExpertMatcher: Automating ML Model Selection for Clients using Hidden Representations
Figure 4 for ExpertMatcher: Automating ML Model Selection for Clients using Hidden Representations
* In NeurIPS Workshop on Robust AI in Financial Services: Data, Fairness, Explainability, Trustworthiness, and Privacy, 2019 
  Access Paper or Ask Questions

ExpertMatcher: Automating ML Model Selection for Users in Resource Constrained Countries


Oct 05, 2019
Vivek Sharma, Praneeth Vepakomma, Tristan Swedish, Ken Chang, Jayashree Kalpathy-Cramer, Ramesh Raskar

Figure 1 for ExpertMatcher: Automating ML Model Selection for Users in Resource Constrained Countries
Figure 2 for ExpertMatcher: Automating ML Model Selection for Users in Resource Constrained Countries
Figure 3 for ExpertMatcher: Automating ML Model Selection for Users in Resource Constrained Countries
Figure 4 for ExpertMatcher: Automating ML Model Selection for Users in Resource Constrained Countries
* In NeurIPS Workshop on Machine learning for the Developing World (ML4D) 
  Access Paper or Ask Questions

Maximal adversarial perturbations for obfuscation: Hiding certain attributes while preserving rest


Sep 27, 2019
Indu Ilanchezian, Praneeth Vepakomma, Abhishek Singh, Otkrist Gupta, G. N. Srinivasa Prasanna, Ramesh Raskar

Figure 1 for Maximal adversarial perturbations for obfuscation: Hiding certain attributes while preserving rest
Figure 2 for Maximal adversarial perturbations for obfuscation: Hiding certain attributes while preserving rest
Figure 3 for Maximal adversarial perturbations for obfuscation: Hiding certain attributes while preserving rest
Figure 4 for Maximal adversarial perturbations for obfuscation: Hiding certain attributes while preserving rest

  Access Paper or Ask Questions

Detailed comparison of communication efficiency of split learning and federated learning


Sep 18, 2019
Abhishek Singh, Praneeth Vepakomma, Otkrist Gupta, Ramesh Raskar

Figure 1 for Detailed comparison of communication efficiency of split learning and federated learning
Figure 2 for Detailed comparison of communication efficiency of split learning and federated learning
Figure 3 for Detailed comparison of communication efficiency of split learning and federated learning
Figure 4 for Detailed comparison of communication efficiency of split learning and federated learning

  Access Paper or Ask Questions

Data Markets to support AI for All: Pricing, Valuation and Governance


May 14, 2019
Ramesh Raskar, Praneeth Vepakomma, Tristan Swedish, Aalekh Sharan

Figure 1 for Data Markets to support AI for All: Pricing, Valuation and Governance
Figure 2 for Data Markets to support AI for All: Pricing, Valuation and Governance
* 7 pages, 2 figures 
  Access Paper or Ask Questions

No Peek: A Survey of private distributed deep learning


Dec 08, 2018
Praneeth Vepakomma, Tristan Swedish, Ramesh Raskar, Otkrist Gupta, Abhimanyu Dubey

Figure 1 for No Peek: A Survey of private distributed deep learning
Figure 2 for No Peek: A Survey of private distributed deep learning
Figure 3 for No Peek: A Survey of private distributed deep learning
Figure 4 for No Peek: A Survey of private distributed deep learning
* 21 pages 
  Access Paper or Ask Questions

Split learning for health: Distributed deep learning without sharing raw patient data


Dec 03, 2018
Praneeth Vepakomma, Otkrist Gupta, Tristan Swedish, Ramesh Raskar

Figure 1 for Split learning for health: Distributed deep learning without sharing raw patient data
Figure 2 for Split learning for health: Distributed deep learning without sharing raw patient data
Figure 3 for Split learning for health: Distributed deep learning without sharing raw patient data
Figure 4 for Split learning for health: Distributed deep learning without sharing raw patient data

  Access Paper or Ask Questions

DISCOMAX: A Proximity-Preserving Distance Correlation Maximization Algorithm


Feb 17, 2017
Praneeth Vepakomma, Ahmed Elgammal

Figure 1 for DISCOMAX: A Proximity-Preserving Distance Correlation Maximization Algorithm
Figure 2 for DISCOMAX: A Proximity-Preserving Distance Correlation Maximization Algorithm
* Withdrawing as an updated and enhanced version of this paper is on arxiv under my name as well titled Supervised Dimensionality Reduction via Distance Correlation Maximization. See arXiv:1601.00236. That makes this version pointless 
  Access Paper or Ask Questions

Optimal bandwidth estimation for a fast manifold learning algorithm to detect circular structure in high-dimensional data


Dec 28, 2016
Susovan Pal, Praneeth Vepakomma

Figure 1 for Optimal bandwidth estimation for a fast manifold learning algorithm to detect circular structure in high-dimensional data
Figure 2 for Optimal bandwidth estimation for a fast manifold learning algorithm to detect circular structure in high-dimensional data
Figure 3 for Optimal bandwidth estimation for a fast manifold learning algorithm to detect circular structure in high-dimensional data
Figure 4 for Optimal bandwidth estimation for a fast manifold learning algorithm to detect circular structure in high-dimensional data
* 19 pages 
  Access Paper or Ask Questions

Supervised Dimensionality Reduction via Distance Correlation Maximization


Jan 03, 2016
Praneeth Vepakomma, Chetan Tonde, Ahmed Elgammal

Figure 1 for Supervised Dimensionality Reduction via Distance Correlation Maximization
Figure 2 for Supervised Dimensionality Reduction via Distance Correlation Maximization
Figure 3 for Supervised Dimensionality Reduction via Distance Correlation Maximization
Figure 4 for Supervised Dimensionality Reduction via Distance Correlation Maximization
* 23 pages, 6 figures 
  Access Paper or Ask Questions