Deepesh Data

University of California, Los Angeles — United States

Computer Science · Physical Sciences

13h-index638citations47works0.52yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Privacy-Preserving Technologies in Data(33), Stochastic Gradient Optimization Techniques(22), Cryptography and Data Security(18), Sparse and Compressive Sensing Techniques(8), Complexity and Algorithms in Graphs(8)

Publications47 total

Decentralized Optimization Resilient Against Local Data Poisoning Attacks
IEEE Transactions on Automatic Control·2024· 1 cited
Utilitarian Privacy and Private Sampling
2024
Byzantine-Resilient High-Dimensional Federated Learning
IEEE Transactions on Information Theory·2023· 12 cited
Must the Communication Graph of MPC Protocols be an Expander?
Journal of Cryptology·2023· 1 citedOpen Access
Communication Efficient Distributed Learning
2023
Decentralized Learning Robust to Data Poisoning Attacks
2022 IEEE 61st Conference on Decision and Control (CDC)·2022· 2 cited
A Generative Framework for Personalized Learning and Estimation: Theory, Algorithms, and Privacy
arXiv (Cornell University)·2022· 2 citedOpen Access
Distributed User-Level Private Mean Estimation
2022 IEEE International Symposium on Information Theory (ISIT)·2022· 3 cited
SPARQ-SGD: Event-Triggered and Compressed Communication in Decentralized Optimization
IEEE Transactions on Automatic Control·2022· 48 cited
Renyi Differential Privacy of The Subsampled Shuffle Model In Distributed Learning
arXiv (Cornell University)·2021Open Access
On the Rényi Differential Privacy of the Shuffle Model
2021· 1 citedOpen Access
Flexible Accuracy for Differential Privacy
arXiv (Cornell University)·2021Open Access
QuPeD: Quantized Personalization via Distillation with Applications to\n Federated Learning
arXiv (Cornell University)·2021· 17 citedOpen Access
QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning
arXiv (Cornell University)·2021· 5 citedOpen Access
Renyi Differential Privacy of the Subsampled Shuffle Model in Distributed Learning
arXiv (Cornell University)·2021· 5 citedOpen Access
Byzantine-Resilient High-Dimensional SGD with Local Iterations on Heterogeneous Data
2021· 3 cited
A Field Guide to Federated Optimization
arXiv (Cornell University)·2021· 167 citedOpen Access
Differentially Private Federated Learning with Shuffling and Client Self-Sampling
2021· 11 cited
SQuARM-SGD: Communication-Efficient Momentum SGD for Decentralized Optimization
2021· 16 citedOpen Access
Byzantine-Resilient SGD in High Dimensions on Heterogeneous Data
2021· 13 citedOpen Access
page 1 of 3Next →

Frequent Co-authors

Suhas Diggavi(35), Antonious M. Girgis(13), Navjot Singh(7), Peter Kairouz(6), Ananda Theertha Suresh(6), Vinod M. Prabhakaran(6), Jemin George(5), Manoj Prabhakaran(5), Kaan Ozkara(4), Linqi Song(3), Can Karakus(2), Navjot Singh(2), Elette Boyle(2), Ran Cohen(2), Pavel Hubáček(2), Yanwen Mao(2), Paulo Tabuada(2), Aman Bansal(2), Rahul Chunduru(2), Jianyu Wang(1)