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

Add to Chrome

Add to Firefox

Picture for A. Salman Avestimehr

A. Salman Avestimehr

Secure Aggregation for Buffered Asynchronous Federated Learning

Oct 05, 2021
Jinhyun So, Ramy E. Ali, Başak Güler, A. Salman Avestimehr

Figure 1 for Secure Aggregation for Buffered Asynchronous Federated Learning

Figure 2 for Secure Aggregation for Buffered Asynchronous Federated Learning

Access Paper or Ask Questions

ApproxIFER: A Model-Agnostic Approach to Resilient and Robust Prediction Serving Systems

Sep 20, 2021
Mahdi Soleymani, Ramy E. Ali, Hessam Mahdavifar, A. Salman Avestimehr

Figure 1 for ApproxIFER: A Model-Agnostic Approach to Resilient and Robust Prediction Serving Systems

Figure 2 for ApproxIFER: A Model-Agnostic Approach to Resilient and Robust Prediction Serving Systems

Figure 3 for ApproxIFER: A Model-Agnostic Approach to Resilient and Robust Prediction Serving Systems

Figure 4 for ApproxIFER: A Model-Agnostic Approach to Resilient and Robust Prediction Serving Systems

Access Paper or Ask Questions

List-Decodable Coded Computing: Breaking the Adversarial Toleration Barrier

Jan 27, 2021
Mahdi Soleymani, Ramy E. Ali, Hessam Mahdavifar, A. Salman Avestimehr

Figure 1 for List-Decodable Coded Computing: Breaking the Adversarial Toleration Barrier

Figure 2 for List-Decodable Coded Computing: Breaking the Adversarial Toleration Barrier

Access Paper or Ask Questions

On Polynomial Approximations for Privacy-Preserving and Verifiable ReLU Networks

Nov 11, 2020
Ramy E. Ali, Jinhyun So, A. Salman Avestimehr

Figure 1 for On Polynomial Approximations for Privacy-Preserving and Verifiable ReLU Networks

Access Paper or Ask Questions

A Scalable Approach for Privacy-Preserving Collaborative Machine Learning

Nov 03, 2020
Jinhyun So, Basak Guler, A. Salman Avestimehr

Figure 1 for A Scalable Approach for Privacy-Preserving Collaborative Machine Learning

Figure 2 for A Scalable Approach for Privacy-Preserving Collaborative Machine Learning

Figure 3 for A Scalable Approach for Privacy-Preserving Collaborative Machine Learning

Figure 4 for A Scalable Approach for Privacy-Preserving Collaborative Machine Learning

Access Paper or Ask Questions

Analog Lagrange Coded Computing

Aug 19, 2020
Mahdi Soleymani, Hessam Mahdavifar, A. Salman Avestimehr

Figure 1 for Analog Lagrange Coded Computing

Figure 2 for Analog Lagrange Coded Computing

Figure 3 for Analog Lagrange Coded Computing

Figure 4 for Analog Lagrange Coded Computing

Access Paper or Ask Questions

Byzantine-Resilient Secure Federated Learning

Jul 21, 2020
Jinhyun So, Basak Guler, A. Salman Avestimehr

Figure 1 for Byzantine-Resilient Secure Federated Learning

Figure 2 for Byzantine-Resilient Secure Federated Learning

Figure 3 for Byzantine-Resilient Secure Federated Learning

Figure 4 for Byzantine-Resilient Secure Federated Learning

* 17 pages, 4 figures

Access Paper or Ask Questions

Privacy-Preserving Distributed Learning in the Analog Domain

Jul 17, 2020
Mahdi Soleymani, Hessam Mahdavifar, A. Salman Avestimehr

Figure 1 for Privacy-Preserving Distributed Learning in the Analog Domain

Figure 2 for Privacy-Preserving Distributed Learning in the Analog Domain

Figure 3 for Privacy-Preserving Distributed Learning in the Analog Domain

Access Paper or Ask Questions

Coded Computing for Federated Learning at the Edge

Jul 14, 2020
Saurav Prakash, Sagar Dhakal, Mustafa Akdeniz, A. Salman Avestimehr, Nageen Himayat

Figure 1 for Coded Computing for Federated Learning at the Edge

Figure 2 for Coded Computing for Federated Learning at the Edge

Figure 3 for Coded Computing for Federated Learning at the Edge

Figure 4 for Coded Computing for Federated Learning at the Edge

* Work accepted for presentation at the International Workshop on Federated Learning for User Privacy and Data Confidentiality, in Conjunction with ICML 2020 (FL-ICML'20). This work was part of Saurav Prakash's internship projects at Intel

Access Paper or Ask Questions

Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks

Jun 16, 2020
Seyed Mohammadreza Mousavi Kalan, Zalan Fabian, A. Salman Avestimehr, Mahdi Soltanolkotabi

Figure 1 for Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks

Figure 2 for Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks

Figure 3 for Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks

Figure 4 for Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks

Access Paper or Ask Questions

Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning

Feb 11, 2020
Jinhyun So, Basak Guler, A. Salman Avestimehr

Figure 1 for Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning

Figure 2 for Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning

Figure 3 for Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning

Figure 4 for Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning

* 19 pages, 8 figures

Access Paper or Ask Questions

CodedPrivateML: A Fast and Privacy-Preserving Framework for Distributed Machine Learning

Feb 02, 2019
Jinhyun So, Basak Guler, A. Salman Avestimehr, Payman Mohassel

Figure 1 for CodedPrivateML: A Fast and Privacy-Preserving Framework for Distributed Machine Learning

Figure 2 for CodedPrivateML: A Fast and Privacy-Preserving Framework for Distributed Machine Learning

Figure 3 for CodedPrivateML: A Fast and Privacy-Preserving Framework for Distributed Machine Learning

Figure 4 for CodedPrivateML: A Fast and Privacy-Preserving Framework for Distributed Machine Learning

* 14 pages, 5 figures

Access Paper or Ask Questions

Fitting ReLUs via SGD and Quantized SGD

Jan 19, 2019
Seyed Mohammadreza Mousavi Kalan, Mahdi Soltanolkotabi, A. Salman Avestimehr

Figure 1 for Fitting ReLUs via SGD and Quantized SGD

Figure 2 for Fitting ReLUs via SGD and Quantized SGD

Figure 3 for Fitting ReLUs via SGD and Quantized SGD

Figure 4 for Fitting ReLUs via SGD and Quantized SGD

Access Paper or Ask Questions

Lagrange Coded Computing: Optimal Design for Resiliency, Security and Privacy

Jun 13, 2018
Qian Yu, Netanel Raviv, Jinhyun So, A. Salman Avestimehr

Figure 1 for Lagrange Coded Computing: Optimal Design for Resiliency, Security and Privacy

Figure 2 for Lagrange Coded Computing: Optimal Design for Resiliency, Security and Privacy

Figure 3 for Lagrange Coded Computing: Optimal Design for Resiliency, Security and Privacy

* Equal contribution from first two authors

Access Paper or Ask Questions

Polynomially Coded Regression: Optimal Straggler Mitigation via Data Encoding

May 24, 2018
Songze Li, Seyed Mohammadreza Mousavi Kalan, Qian Yu, Mahdi Soltanolkotabi, A. Salman Avestimehr

Figure 1 for Polynomially Coded Regression: Optimal Straggler Mitigation via Data Encoding

Figure 2 for Polynomially Coded Regression: Optimal Straggler Mitigation via Data Encoding

Figure 3 for Polynomially Coded Regression: Optimal Straggler Mitigation via Data Encoding

Figure 4 for Polynomially Coded Regression: Optimal Straggler Mitigation via Data Encoding

Access Paper or Ask Questions

Fundamental Resource Trade-offs for Encoded Distributed Optimization

Mar 31, 2018
A. Salman Avestimehr, Seyed Mohammadreza Mousavi Kalan, Mahdi Soltanolkotabi

Figure 1 for Fundamental Resource Trade-offs for Encoded Distributed Optimization

Figure 2 for Fundamental Resource Trade-offs for Encoded Distributed Optimization

Access Paper or Ask Questions

Coded Fourier Transform

Oct 17, 2017
Qian Yu, Mohammad Ali Maddah-Ali, A. Salman Avestimehr

Figure 1 for Coded Fourier Transform

Figure 2 for Coded Fourier Transform

Access Paper or Ask Questions

Active Learning On Weighted Graphs Using Adaptive And Non-adaptive Approaches

May 18, 2016
Eyal En Gad, Akshay Gadde, A. Salman Avestimehr, Antonio Ortega

Figure 1 for Active Learning On Weighted Graphs Using Adaptive And Non-adaptive Approaches

Figure 2 for Active Learning On Weighted Graphs Using Adaptive And Non-adaptive Approaches

Figure 3 for Active Learning On Weighted Graphs Using Adaptive And Non-adaptive Approaches

* In ICASSP 2016

Access Paper or Ask Questions

Asymptotic Justification of Bandlimited Interpolation of Graph signals for Semi-Supervised Learning

Feb 14, 2015
Aamir Anis, Aly El Gamal, A. Salman Avestimehr, Antonio Ortega

Figure 1 for Asymptotic Justification of Bandlimited Interpolation of Graph signals for Semi-Supervised Learning

Figure 2 for Asymptotic Justification of Bandlimited Interpolation of Graph signals for Semi-Supervised Learning

Figure 3 for Asymptotic Justification of Bandlimited Interpolation of Graph signals for Semi-Supervised Learning

* To appear in ICASSP 2015, 5 pages, 3 figures

Access Paper or Ask Questions