Continuous LWE

05/19/2020
by   Joan Bruna, et al.
0

We introduce a continuous analogue of the Learning with Errors (LWE) problem, which we name CLWE. We give a polynomial-time quantum reduction from worst-case lattice problems to CLWE, showing that CLWE enjoys similar hardness guarantees to those of LWE. Alternatively, our result can also be seen as opening new avenues of (quantum) attacks on lattice problems. Our work resolves an open problem regarding the computational complexity of learning mixtures of Gaussians without separability assumptions (Diakonikolas 2016, Moitra 2018). As an additional motivation, (a slight variant of) CLWE was considered in the context of robust machine learning (Diakonikolas et al. FOCS 2017), where hardness in the statistical query (SQ) model was shown; our work addresses the open question regarding its computational hardness (Bubeck et al. ICML 2019).

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

06/20/2021

On the Cryptographic Hardness of Learning Single Periodic Neurons

We show a simple reduction which demonstrates the cryptographic hardness...
08/11/2020

The Polynomial Learning With Errors Problem and the Smearing Condition

As quantum computing advances rapidly, guaranteeing the security of cryp...
05/10/2018

ETH-Hardness of Approximating 2-CSPs and Directed Steiner Network

We study the 2-ary constraint satisfaction problems (2-CSPs), which can ...
08/25/2021

Quantum Algorithms for Variants of Average-Case Lattice Problems via Filtering

We show polynomial-time quantum algorithms for the following problems: ...
04/29/2021

Quantum speedups for dynamic programming on n-dimensional lattice graphs

Motivated by the quantum speedup for dynamic programming on the Boolean ...
09/28/2018

A Candidate Group with Infeasible Inversion

Motivated by the potential cryptographic application of building a direc...
08/19/2019

Filletting Quador Lattice Structures

Gupta et al. [1, 2] describe a very beautiful application of algebraic g...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.