Practically Solving LPN in High Noise Regimes Faster Using Neural Networks

by   Haozhe Jiang, et al.
Tsinghua University

We conduct a systematic study of solving the learning parity with noise problem (LPN) using neural networks. Our main contribution is designing families of two-layer neural networks that practically outperform classical algorithms in high-noise, low-dimension regimes. We consider three settings where the numbers of LPN samples are abundant, very limited, and in between. In each setting we provide neural network models that solve LPN as fast as possible. For some settings we are also able to provide theories that explain the rationale of the design of our models. Comparing with the previous experiments of Esser, Kubler, and May (CRYPTO 2017), for dimension n = 26, noise rate τ = 0.498, the ”Guess-then-Gaussian-elimination” algorithm takes 3.12 days on 64 CPU cores, whereas our neural network algorithm takes 66 minutes on 8 GPUs. Our algorithm can also be plugged into the hybrid algorithms for solving middle or large dimension LPN instances.


page 1

page 2

page 3

page 4


Designing Network Design Spaces

In this work, we present a new network design paradigm. Our goal is to h...

Multivariate Forecasting of Crude Oil Spot Prices using Neural Networks

Crude oil is a major component in most advanced economies of the world. ...

Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks

In recent years, several results in the supervised learning setting sugg...

Solving the Dirichlet problem for the Monge-Ampère equation using neural networks

The Monge-Ampère equation is a fully nonlinear partial differential equa...

Solving Sinhala Language Arithmetic Problems using Neural Networks

A methodology is presented to solve Arithmetic problems in Sinhala Langu...

NNS: The Case For Neural Network-based Sorting

CPU-SIMD/GPU/TPUs will be increasingly powerful. The algorithm using neu...

A Principle of Least Action for the Training of Neural Networks

Neural networks have been achieving high generalization performance on m...

Code Repositories


This repository is the official codebase the for paper Practically Solving LPN in High Noise Regimes Faster Using Neural Networks

view repo

Please sign up or login with your details

Forgot password? Click here to reset