Sublinear classical and quantum algorithms for general matrix games

12/11/2020
by   Tongyang Li, et al.
3

We investigate sublinear classical and quantum algorithms for matrix games, a fundamental problem in optimization and machine learning, with provable guarantees. Given a matrix A∈ℝ^n× d, sublinear algorithms for the matrix game min_x∈𝒳max_y∈𝒴 y^⊤ Ax were previously known only for two special cases: (1) 𝒴 being the ℓ_1-norm unit ball, and (2) 𝒳 being either the ℓ_1- or the ℓ_2-norm unit ball. We give a sublinear classical algorithm that can interpolate smoothly between these two cases: for any fixed q∈ (1,2], we solve the matrix game where 𝒳 is a ℓ_q-norm unit ball within additive error ϵ in time Õ((n+d)/ϵ^2). We also provide a corresponding sublinear quantum algorithm that solves the same task in time Õ((√(n)+√(d))poly(1/ϵ)) with a quadratic improvement in both n and d. Both our classical and quantum algorithms are optimal in the dimension parameters n and d up to poly-logarithmic factors. Finally, we propose sublinear classical and quantum algorithms for the approximate Carathéodory problem and the ℓ_q-margin support vector machines as applications.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/04/2019

Sublinear quantum algorithms for training linear and kernel-based classifiers

We investigate quantum algorithms for classification, a fundamental prob...
research
06/12/2020

Quantum-over-classical Advantage in Solving Multiplayer Games

We study the applicability of quantum algorithms in computational game t...
research
04/27/2023

Logarithmic-Regret Quantum Learning Algorithms for Zero-Sum Games

We propose the first online quantum algorithm for zero-sum games with Õ(...
research
07/03/2019

Variance Reduction for Matrix Games

We present a randomized primal-dual algorithm that solves the problem _x...
research
11/03/2017

An homotopy method for ℓ_p regression provably beyond self-concordance and in input-sparsity time

We consider the problem of linear regression where the ℓ_2^n norm loss (...
research
07/13/2023

Fast and Practical Quantum-Inspired Classical Algorithms for Solving Linear Systems

We propose fast and practical quantum-inspired classical algorithms for ...
research
06/08/2020

Quantum Logspace Algorithm for Powering Matrices with Bounded Norm

We give a quantum logspace algorithm for powering contraction matrices, ...

Please sign up or login with your details

Forgot password? Click here to reset