# Selective Network Linearization for Efficient Private Inference Source: [Selective Network Linearization for Efficient Private Inference]() Collection index: [llms.txt]() Data updated: 2025-10-28T13:56:53.744Z Authors: Minsu Cho, Ameya Joshi, Siddharth Garg, Brandon Reagen, Chinmay Hegde Published: 2022-02-04T19:00:24.000Z ## Abstract Private inference (PI) enables inference directly on cryptographically secure data.While promising to address many privacy issues, it has seen limited use due to extreme runtimes. Unlike plaintext inference, where latency is dominated by FLOPs, in PI non-linear functions (namely ReLU) are the bottleneck. Thus, practical PI demands novel ReLU-aware optimizations. To reduce PI latency we propose a gradient-based algorithm that selectively linearizes ReLUs while maintaining prediction accuracy. We evaluate our algorithm on several standard PI benchmarks. The results demonstrate up to $4.25\\%$ more accuracy (iso-ReLU count at 50K) or $2.2\\times$ less latency (iso-accuracy at 70\\%) than the current state of the art and advance the Pareto frontier across the latency-accuracy space. To complement empirical results, we present a "no free lunch" theorem that sheds light on how and when network linearization is possible while maintaining prediction accuracy. Public code is available at \\url{https://github.com/NYU-DICE-Lab/selective\_network\_linearization}. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on CIFAR-100 (Acc. (%) and Acc./#ReLU)](): Image Classification; CIFAR-100; Accuracy (%): 73.75. ## Original sources and implementation [Original paper]() [PDF]()