Efficient ML

Characterizing and Optimizing End-to-End Systems for Private Inference

Studies private inference as an end-to-end systems problem, identifying bottlenecks across the full stack and optimizing performance beyond isolated model changes.

Karthik Garimella, Zahra Ghodsi, Nandan Kumar Jha, Siddharth Garg, Brandon Reagen

Characterizing and Optimizing End-to-End Systems for Private Inference

DeepReDuce: ReLU Reduction for Fast Private Inference

ICML spotlight talk on criticality-based ReLU reduction for fast private inference.

Jul 1, 2021 Virtual Conference