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

no code implementations • 20 Sep 2021 • Mahdi Soleymani, Ramy E. Ali, Hessam Mahdavifar, A. Salman Avestimehr

While this learning-based approach is more resource-efficient than replication, it is tailored to the specific model hosted by the cloud and is particularly suitable for a small number of queries (typically less than four) and tolerating very few (mostly one) number of stragglers.

List-Decodable Coded Computing: Breaking the Adversarial Toleration Barrier

no code implementations • 27 Jan 2021 • Mahdi Soleymani, Ramy E. Ali, Hessam Mahdavifar, A. Salman Avestimehr

We further propose folded Lagrange coded computing (FLCC) to incorporate the developed techniques into a specific coded computing setting.

Decoder

Analog Lagrange Coded Computing

no code implementations • 19 Aug 2020 • Mahdi Soleymani, Hessam Mahdavifar, A. Salman Avestimehr

Also, the accuracy of outcome is characterized in a practical setting assuming operations are performed using floating-point numbers.

Distributed Computing

Privacy-Preserving Distributed Learning in the Analog Domain

no code implementations • 17 Jul 2020 • Mahdi Soleymani, Hessam Mahdavifar, A. Salman Avestimehr

Then numerical results are shown for experiments on the MNIST dataset.

Privacy Preserving