The most important computational problem on lattices is the Shortest Vector Problem (SVP). In this paper, we present new algorithms that improve the state-of-the-art for provable classical/quantum algorithms for SVP. We present the following results. 1) A new algorithm for SVP that provides a smooth tradeoff between time complexity and memory requirement. For any positive integer 4 ≤ q ≤ √n, our algorithm takes q^{13n+o(n)} time and requires poly(n)⋅ q^{16n/q²} memory. This tradeoff which ranges from enumeration (q = √n) to sieving (q constant), is a consequence of a new time-memory tradeoff for Discrete Gaussian sampling above the smoothing parameter. 2) A quantum algorithm that runs in time 2^{0.9533n+o(n)} and requires 2^{0.5n+o(n)} classical memory and poly(n) qubits. This improves over the previously fastest classical (which is also the fastest quantum) algorithm due to [Divesh Aggarwal et al., 2015] that has a time and space complexity 2^{n+o(n)}. 3) A classical algorithm for SVP that runs in time 2^{1.741n+o(n)} time and 2^{0.5n+o(n)} space. This improves over an algorithm of [Yanlin Chen et al., 2018] that has the same space complexity. The time complexity of our classical and quantum algorithms are expressed using a quantity related to the kissing number of a lattice. A known upper bound of this quantity is 2^{0.402n}, but in practice for most lattices, it can be much smaller and even 2^o(n). In that case, our classical algorithm runs in time 2^{1.292n} and our quantum algorithm runs in time 2^{0.750n}.
The most important computational problem on lattices is the Shortest Vector Problem (SVP). In this paper, we present new algorithms that improve the state-of-the-art for provable classical/quantum algorithms for SVP. We present the following results. 1) A new algorithm for SVP that provides a smooth tradeoff between time complexity and memory requirement. For any positive integer 4 ≤ q ≤ √n, our algorithm takes q^{13n+o(n)} time and requires poly(n)⋅ q^{16n/q²} memory. This tradeoff which ranges from enumeration (q = √n) to sieving (q constant), is a consequence of a new time-memory tradeoff for Discrete Gaussian sampling above the smoothing parameter. 2) A quantum algorithm that runs in time 2^{0.9533n+o(n)} and requires 2^{0.5n+o(n)} classical memory and poly(n) qubits. This improves over the previously fastest classical (which is also the fastest quantum) algorithm due to [Divesh Aggarwal et al., 2015] that has a time and space complexity 2^{n+o(n)}. 3) A classical algorithm for SVP that runs in time 2^{1.741n+o(n)} time and 2^{0.5n+o(n)} space. This improves over an algorithm of [Yanlin Chen et al., 2018] that has the same space complexity. The time complexity of our classical and quantum algorithms are expressed using a quantity related to the kissing number of a lattice. A known upper bound of this quantity is 2^{0.402n}, but in practice for most lattices, it can be much smaller and even 2^o(n). In that case, our classical algorithm runs in time 2^{1.292n} and our quantum algorithm runs in time 2^{0.750n}.
The most important computational problem on lattices is the Shortest Vector Problem (SVP). In this paper, we present new algorithms that improve the state-of-the-art for provable classical/quantum algorithms for SVP. We present the following results. ∙ A new algorithm for SVP that provides a smooth tradeoff between time complexity and memory requirement. For any positive integer 4≤q≤n, our algorithm takes q13n+o(n) time and requires poly(n)⋅q16n/q2 memory. This tradeoff which ranges from enumeration (q=n) to sieving (q constant), is a consequence of a new time-memory tradeoff for Discrete Gaussian sampling above the smoothing parameter. ∙ A quantum algorithm for SVP that runs in time 20.950n+o(n) and requires 20.5n+o(n) classical memory and poly(n) qubits. In Quantum Random Access Memory (QRAM) model this algorithm takes only 20.835n+o(n) time and requires a QRAM of size 20.293n+o(n), poly(n) qubits and 20.5n classical space. This improves over the previously fastest classical (which is also the fastest quantum) algorithm due to [ADRS15] that has a time and space complexity 2n+o(n). ∙ A classical algorithm for SVP that runs in time 21.669n+o(n) time and 20.5n+o(n) space. This improves over an algorithm of [CCL18] that has the same space complexity. The time complexity of our classical and quantum algorithms are obtained using a known upper bound on a quantity related to the lattice kissing number which is 20.402n. We conjecture that for most lattices this quantity is a 2o(n). Assuming that this is the case, our classical algorithm runs in time 21.292n+o(n), our quantum algorithm runs in time 20.750n+o(n) and our quantum algorithm in QRAM model runs in time 20.667n+o(n).
Abstract. The most important computational problem on lattices is the shortest vector problem ([Formula: see text]). In this paper, we present new algorithms that improve the state-of-the-art for provable classical/quantum algorithms for [Formula: see text]. We present the following results: (1) A new algorithm for [Formula: see text] that provides a smooth tradeoff between time complexity and memory requirement. For any positive integer [Formula: see text], our algorithm takes [Formula: see text] time and requires [Formula: see text] memory. This tradeoff, which ranges from enumeration ([Formula: see text]) to sieving ([Formula: see text] constant), is a consequence of a new time-memory tradeoff for discrete Gaussian sampling above the smoothing parameter. (2) A quantum algorithm for [Formula: see text] that runs in time [Formula: see text] and requires [Formula: see text] classical memory and [Formula: see text] qubits. In a quantum random access memory (QRAM) model, this algorithm takes only [Formula: see text] time and requires a QRAM of size [Formula: see text], [Formula: see text] qubits and [Formula: see text] classical space. This improves over the previously fastest classical (which is also the fastest quantum) algorithm due to [D. Aggarwal et al., Solving the shortest vector problem in 2 n time using discrete Gaussian sampling: Extended abstract, in Proceedings of the Forty-Seventh Annual ACM on Symposium on Theory of Computing (STOC), 2015, pp. 733–742] that has a time and space complexity [Formula: see text]. (3) A classical algorithm for [Formula: see text] that runs in time [Formula: see text] time and [Formula: see text] space. This improves over an algorithm of [Y. Chen, K. Chung, and C. Lai, Quantum Inf. Comput., 18 (2018), pp. 285–306] that has the same space complexity. The time complexity of our classical and quantum algorithms are obtained using a known upper bound on a quantity related to the lattice kissing number, which is [Formula: see text]. We conjecture that for most lattices this quantity is a [Formula: see text]. Assuming that this is the case, our classical algorithm runs in time [Formula: see text], our quantum algorithm runs in time [Formula: see text], and our quantum algorithm in a QRAM model runs in time [Formula: see text]. As a direct application of our result, using the reduction in [L. Ducas, Des. Codes. Cryptogr., 92 (2024), pp. 909–916], we obtain a provable quantum algorithm for the lattice isomorphism problem in the case of the trivial lattice [Formula: see text] ([Formula: see text] LIP ) that runs in time [Formula: see text]. Our algorithm requires a QRAM of size [Formula: see text], [Formula: see text] qubits and [Formula: see text] classical space.
A lattice is the integer span of some linearly independent vectors. Lattice problems have many significant applications in coding theory and cryptographic systems for their conjectured hardness. The Shortest Vector Problem (SVP), which asks to find a shortest nonzero vector in a lattice, is one of the well-known problems that are believed to be hard to solve, even with a quantum computer. In this paper we propose space-efficient classical and quantum algorithms for solving SVP. Currently the best time-efficient algorithm for solving SVP takes 2^{n+o(n)} time and 2^{n+o(n)} space. Our classical algorithm takes 2^{2.05n+o(n)} time to solve SVP and it requires only 2^{0.5n+o(n)} space. We then adapt our classical algorithm to a quantum version, which can solve SVP in time 2^{1.2553n+o(n)} with 2^{0.5n+o(n)} classical space and only poly(n) qubits.
Finding the shortest non-zero vector on a lattice is a fundamental problem in lattices that is believed to be hard both for classical and quantum computers. Two of the three standardised by NIST post-quantum cryptosystems rely on its hardness. Research on theoretical and practical performance of quantum algorithms to solve the Shortest Vector Problem (SVP) is crucial to establish confidence in those new standards. Exploring the capabilities that Variational Quantum Algorithms (VQA) that can run on Noisy Intermediate Scale Quantum (NISQ) devices have in solving SVP has been an active area of research. The qubit-requirement for doing so has been analysed and demonstrated that it is plausible to encode SVP on the ground state of a Hamiltonian in an efficient way. Due to the heuristic nature of VQAs no analysis of the performance and specifically of the time complexity of those approaches for scales beyond the non-interesting classically simulatable sizes has been performed. In this paper, motivated by Boulebnane and Montanaro [1] work on the k-SAT problem, we propose to use angle pretraining of the Quantum Approximate Optimisation Algorithm (QAOA) for SVP and we demonstrate that QAOA with fixed angles performs well on much larger instances than those used in training. Avoiding the limitations that arise due to the use of optimiser, we are able to extrapolate the observed performance and we observe the probability of success scaling as2−0.695nwithnbeing dimensionality of the search space for a depthp=3pre-trained QAOA algorithm. By repeating the algorithm, we get heuristic time complexityO(20.695n)to solve the problem with high probability, a bit worse than the fault-tolerant Grover approach ofO(20.5n). On the other hand, both the number of qubits, and most importantly the depth of each quantum computation, are considerably better in our approach – Grover requires exponential depth, while each run of constantpfixed-angles QAOA requires polynomial depth. Further, we analyse the performance of QAOA in solving approximate-SVP, a version of the problem that one seeks a multiplicative approximation to the shortest vector. As a side result, we propose a novel method to avoid the zero vector solution to SVP without introducing more logical qubits. This improves upon the previous works as it results in more space efficient encoding of SVP on NISQ architectures without ignoring the zero vector problem.
Solving the Shortest Vector Problem in 20.6039n Time via Mid-point Hessian
We present randomized algorithms for the shortest vector problem (SVP). For the n-dimensional lattice L, our algorithms solve SVP in time 20.6039n+o(n) classically and 20.5411n+o(n) quantumly and space 20.5n+o(n), improving the previous best algorithm running in 2n+o(n) time and space of Aggarwal, Dadush, Regev, and Stephens-Davidowitz [STOC'15]. Our algorithms heavily use the property of the Hessian of the periodic Gaussian function at the half shortest vector: For a shortest vector v∈L, the Hessian at v/2 has the eigenvector close to v, which can be used to recover v using the (preprocessing) bounded distance decoding algorithm. Given the periodicity modulo L, the candidate midpoints are indexed by the parity classes in L/2L. Our algorithm searches for the class of a shortest vector by estimating the corresponding Hessians using discrete Gaussian samples. We optimize the algorithm using random sublattice cosets and various sampling technique, achieving the final complexity. The optimization techniques may be of independent interest.
A fundamental computational problem is to find a shortest non-zero vector in Euclidean lattices, a problem known as the Shortest Vector Problem (SVP). This problem is believed to be hard even on quantum computers and thus plays a pivotal role in post-quantum cryptography. In this work we explore how (efficiently) Noisy Intermediate Scale Quantum (NISQ) devices may be used to solve SVP. Specifically, we map the problem to that of finding the ground state of a suitable Hamiltonian. In particular, (i) we establish new bounds for lattice enumeration, this allows us to obtain new bounds (resp. estimates) for the number of qubits required per dimension for any lattices (resp. random q-ary lattices) to solve SVP; (ii) we exclude the zero vector from the optimization space by proposing (a) a different classical optimisation loop or alternatively (b) a new mapping to the Hamiltonian. These improvements allow us to solve SVP in dimension up to 28 in a quantum emulation, significantly more than what was previously achieved, even for special cases. Finally, we extrapolate the size of NISQ devices that is required to be able to solve instances of lattices that are hard even for the best classical algorithms and find that with approximately 103 noisy qubits such instances can be tackled.