On the Cryptographic Hardness of Learning Single Periodic Neurons

by   Min Jae Song, et al.

We show a simple reduction which demonstrates the cryptographic hardness of learning a single periodic neuron over isotropic Gaussian distributions in the presence of noise. More precisely, our reduction shows that any polynomial-time algorithm (not necessarily gradient-based) for learning such functions under small noise implies a polynomial-time quantum algorithm for solving worst-case lattice problems, whose hardness form the foundation of lattice-based cryptography. Our core hard family of functions, which are well-approximated by one-layer neural networks, take the general form of a univariate periodic function applied to an affine projection of the data. These functions have appeared in previous seminal works which demonstrate their hardness against gradient-based (Shamir'18), and Statistical Query (SQ) algorithms (Song et al.'17). We show that if (polynomially) small noise is added to the labels, the intractability of learning these functions applies to all polynomial-time algorithms, beyond gradient-based and SQ algorithms, under the aforementioned cryptographic assumptions. Moreover, we demonstrate the necessity of noise in the hardness result by designing a polynomial-time algorithm for learning certain families of such functions under exponentially small adversarial noise. Our proposed algorithm is not a gradient-based or an SQ algorithm, but is rather based on the celebrated Lenstra-Lenstra-Lovász (LLL) lattice basis reduction algorithm. Furthermore, in the absence of noise, this algorithm can be directly applied to solve CLWE detection (Bruna et al.'21) and phase retrieval with an optimal sample complexity of d+1 samples. In the former case, this improves upon the quadratic-in-d sample complexity required in (Bruna et al.'21).



There are no comments yet.


page 1

page 2

page 3

page 4


Continuous LWE

We introduce a continuous analogue of the Learning with Errors (LWE) pro...

Lattice-Based Methods Surpass Sum-of-Squares in Clustering

Clustering is a fundamental primitive in unsupervised learning which giv...

Halt Properties and Complexity Evaluations for Optimal DeepLLL Algorithm Families

DeepLLL algorithm (Schnorr, 1994) is a famous variant of LLL lattice bas...

Hardness of learning noisy halfspaces using polynomial thresholds

We prove the hardness of weakly learning halfspaces in the presence of a...

Continuous LWE is as Hard as LWE Applications to Learning Gaussian Mixtures

We show direct and conceptually simple reductions between the classical ...

On the Sample Complexity of solving LWE using BKW-Style Algorithms

The Learning with Errors (LWE) problem receives much attention in crypto...

Inference in High-Dimensional Linear Regression via Lattice Basis Reduction and Integer Relation Detection

We focus on the high-dimensional linear regression problem, where the al...
This week in AI

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