Litcius/Paper detail

Quantum Differentially Private Sparse Regression Learning

Yuxuan Du, Min-Hsiu Hsieh, Tongliang Liu, Shan You, Dacheng Tao

2022IEEE Transactions on Information Theory30 citationsDOIOpen Access PDF

Abstract

The eligibility of various advanced quantum algorithms will be questioned if they can not guarantee privacy. To fill this knowledge gap, here we devise an efficient quantum differentially private (QDP) Lasso estimator to solve sparse regression tasks. Concretely, given <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$N~d$ </tex-math></inline-formula> -dimensional data points with <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$N\ll d$ </tex-math></inline-formula> , we first prove that the optimal classical and quantum non-private Lasso requires <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\Omega (N+d)$ </tex-math></inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\Omega (\sqrt {N}+\sqrt {d})$ </tex-math></inline-formula> runtime, respectively. We next prove that the runtime cost of QDP Lasso is <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">dimension independent</i> , i.e., <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$O(N^{5/2})$ </tex-math></inline-formula> , which implies that the QDP Lasso can be faster than both the optimal classical and quantum non-private Lasso. Last, we exhibit that the QDP Lasso attains a near-optimal utility bound <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\tilde {O}(N^{-2/3})$ </tex-math></inline-formula> with privacy guarantees and discuss the chance to realize it on near-term quantum chips with advantages.

Topics & Concepts

Lasso (programming language)EstimatorQuantumDimension (graph theory)OmegaElastic net regularizationMathematicsComputer scienceAlgorithmDiscrete mathematicsCombinatoricsRegressionPhysicsStatisticsQuantum mechanicsWorld Wide WebStochastic Gradient Optimization TechniquesQuantum Computing Algorithms and ArchitecturePrivacy-Preserving Technologies in Data
Quantum Differentially Private Sparse Regression Learning | Litcius