The Fine-Grained Hardness of Sparse Linear Regression

by   Aparna Gupte, et al.

Sparse linear regression is the well-studied inference problem where one is given a design matrix π€βˆˆβ„^MΓ— N and a response vector π›βˆˆβ„^M, and the goal is to find a solution π±βˆˆβ„^N which is k-sparse (that is, it has at most k non-zero coordinates) and minimizes the prediction error ||𝐀𝐱 - 𝐛||_2. On the one hand, the problem is known to be 𝒩𝒫-hard which tells us that no polynomial-time algorithm exists unless 𝒫 = 𝒩𝒫. On the other hand, the best known algorithms for the problem do a brute-force search among N^k possibilities. In this work, we show that there are no better-than-brute-force algorithms, assuming any one of a variety of popular conjectures including the weighted k-clique conjecture from the area of fine-grained complexity, or the hardness of the closest vector problem from the geometry of numbers. We also show the impossibility of better-than-brute-force algorithms when the prediction error is measured in other β„“_p norms, assuming the strong exponential-time hypothesis.


page 1

page 2

page 3

page 4

βˆ™ 06/29/2022

Hardness and Algorithms for Robust and Sparse Optimization

We explore algorithms and limitations for sparse optimization problems s...
βˆ™ 06/24/2021

Optimal Fine-grained Hardness of Approximation of Linear Equations

The problem of solving linear systems is one of the most fundamental pro...
βˆ™ 03/17/2020

Hardness of Bounded Distance Decoding on Lattices in β„“_p Norms

Bounded Distance Decoding _p,Ξ± is the problem of decoding a lattice when...
βˆ™ 05/23/2020

Finding Small Satisfying Assignments Faster Than Brute Force: A Fine-grained Perspective into Boolean Constraint Satisfaction

To study the question under which circumstances small solutions can be f...
βˆ™ 04/10/2017

On the Fine-Grained Complexity of Empirical Risk Minimization: Kernel Methods and Neural Networks

Empirical risk minimization (ERM) is ubiquitous in machine learning and ...
βˆ™ 10/23/2015

On the complexity of switching linear regression

This technical note extends recent results on the computational complexi...
βˆ™ 09/09/2021

Improved Hardness of BDD and SVP Under Gap-(S)ETH

We show improved fine-grained hardness of two key lattice problems in th...