# PRANC: Pseudo RAndom Networks for Compacting deep models

Source: [PRANC: Pseudo RAndom Networks for Compacting deep models](<https://www.sota2.com/research/paper/68fa70771e209131cea4b452>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:42:00.795Z

Authors: Parsa Nooralinejad, Ali Abbasi, Soroush Abbasi Koohpayegani, Kossar Pourahmadi Meibodi, Rana Muhammad Shahroz Khan, Soheil Kolouri, Hamed Pirsiavash

Published: 2022-06-16T22:03:35.000Z

## Abstract

We demonstrate that a deep model can be reparametrized as a linear combination of several randomly initialized and frozen deep models in the weight space. During training, we seek local minima that reside within the subspace spanned by these random models (i.e., \`basis' networks). Our framework, PRANC, enables significant compaction of a deep model. The model can be reconstructed using a single scalar \`seed,' employed to generate the pseudo-random \`basis' networks, together with the learned linear mixture coefficients.   In practical applications, PRANC addresses the challenge of efficiently storing and communicating deep models, a common bottleneck in several scenarios, including multi-agent learning, continual learners, federated systems, and edge devices, among others. In this study, we employ PRANC to condense image classification models and compress images by compacting their associated implicit neural networks. PRANC outperforms baselines with a large margin on image classification when compressing a deep model almost $100$ times. Moreover, we show that PRANC enables memory-efficient inference by generating layer-wise weights on the fly. The source code of PRANC is here: \\url{https://github.com/UCDvision/PRANC}

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2206.08464>)

[PDF](<https://arxiv.org/pdf/2206.08464.pdf>)