DeepAI
Log In Sign Up

Quantum Regularized Least Squares

06/27/2022
by   Shantanav Chakraborty, et al.
0

Linear regression is a widely used technique to fit linear models and finds widespread applications across different areas such as machine learning and statistics. In most real-world scenarios, however, linear regression problems are often ill-posed or the underlying model suffers from overfitting, leading to erroneous or trivial solutions. This is often dealt with by adding extra constraints, known as regularization. In this paper, we use the frameworks of block-encoding and quantum singular value transformation (QSVT) to design the first quantum algorithms for quantum least squares with general ℓ_2-regularization. These include regularized versions of quantum ordinary least squares, quantum weighted least squares, and quantum generalized least squares. Our quantum algorithms substantially improve upon prior results on quantum ridge regression (polynomial improvement in the condition number and an exponential improvement in accuracy), which is a particular case of our result. To this end, we assume approximate block-encodings of the underlying matrices as input and use robust QSVT algorithms for various linear algebra operations. In particular, we develop a variable-time quantum algorithm for matrix inversion using QSVT, where we use quantum eigenvalue discrimination as a subroutine instead of gapped phase estimation. This ensures that substantially fewer ancilla qubits are required for this procedure than prior results. Owing to the generality of the block-encoding framework, our algorithms are applicable to a variety of input models and can also be seen as improved and generalized versions of prior results on standard (non-regularized) quantum least squares algorithms.

READ FULL TEXT

page 1

page 2

page 3

page 4

04/05/2018

The power of block-encoded matrix powers: improved regression techniques via faster Hamiltonian simulation

We apply the framework of block-encodings, introduced by Low and Chuang ...
03/19/2022

Explicit Quantum Circuits for Block Encodings of Certain Sparse Matrices

Many standard linear algebra problems can be solved on a quantum compute...
10/04/2022

Quantum communication complexity of linear regression

Dequantized algorithms show that quantum computers do not have exponenti...
02/22/2018

Quantum linear systems algorithms: a primer

The Harrow-Hassidim-Lloyd (HHL) quantum algorithm for sampling from the ...
09/15/2020

An improved quantum-inspired algorithm for linear regression

We give a classical algorithm for linear regression analogous to the qua...
05/01/2019

Quantum Generalized Linear Models

Generalized linear models (GLM) are link function based statistical mode...
08/04/2022

Spectral Universality of Regularized Linear Regression with Nearly Deterministic Sensing Matrices

It has been observed that the performances of many high-dimensional esti...