Finding the minimum value in an unordered database is a common and fundamental task in computer science. However, the optimal classical deterministic algorithm can find the minimum value with a time complexity that grows linearly with the number of elements in the database. In this paper, we present the proposal of a quantum algorithm for finding the minimum value of a database, which is quadratically faster than its best classical analogs. We assume a Quantum Random Access Memory (QRAM) that stores values from a database and perform an iterative search based on an oracle whose role is to limit the searched values by controlling the states of the most significant qubits. A complexity analysis was performed in order to demonstrate the advantage of this quantum algorithm over its classical counterparts. Furthermore, we demonstrate how the proposed algorithm would be used in an unsupervised machine learning task through a quantum version of the K-means algorithm.
Finding the minimum value in an unordered database is a common and fundamental task in computer science. However, the optimal classical deterministic algorithm can find the minimum value with a time complexity that grows linearly with the number of elements in the database. In this paper, we present the proposal of a quantum algorithm for finding the minimum value of a database, which is quadratically faster than its best classical analogs. We assume a Quantum Random Access Memory (QRAM) that stores values from a database and perform an iterative search based on an oracle whose role is to limit the searched values by controlling the states of the most significant qubits. A complexity analysis was performed in order to demonstrate the advantage of this quantum algorithm over its classical counterparts. Furthermore, we demonstrate how the proposed algorithm would be used in an unsupervised machine learning task through a quantum version of the K-means algorithm.
Abstract Finding the minimum value in an unordered database is a common and fundamental task in computer science. However, the optimal classical deterministic algorithm can find the minimum value with a time complexity that grows linearly with the number of elements in the database. In this paper, we present the proposal of a quantum algorithm for finding the minimum value of a database, which is quadratically faster than its best classical analogs. We assume a Quantum Random Access Memory (QRAM) that stores values from a database and performs an iterative search based on an oracle whose role is to limit the searched values by controlling the states of the most significant qubits. A complexity analysis was performed in order to demonstrate the advantage of this quantum algorithm over its classical counterparts.
Quantum Random Access Memory (QRAM) represents a crucial component in the realization of practical quantum computers, enabling fast and probabilistic data access for quantum algorithms. However, accurately simulating QRAM's operation presents a formidable challenge due to the inherent randomness and quantum mechanical nature of the system. This work investigates and proposes novel simulation techniques and optimization algorithms aimed at mitigating this computational complexity. We explore various approaches, including stochastic simulation methods, reduced-order modeling, and tailored optimization strategies, focusing on minimizing the number of quantum operations required for accurate QRAM simulation. The results demonstrate significant reductions in computational cost while maintaining a reasonable level of fidelity, paving the way for more efficient design and analysis of QRAM architectures. The core claim of this research is that the development of QRAM is fundamentally limited by the complexity of its simulation, and this work offers a direct path toward overcoming this bottleneck.
A quantum computer encodes information in quantum states and runs quantum algorithms to surpass the classical counterparts by exploiting quantum superposition and quantum correlation. Grover's quantum search algorithm is a typical quantum algorithm that proves the superiority of quantum computing over classical computing. It has a quadratic reduction in the query complexity of a database search and is known to be optimal when no a priori information about the elements of the database is provided. In this work we consider a probabilistic Grover search algorithm allowing nonzero probability of failure for a database with a general a priori probability distribution of the elements and minimize the number of oracle calls by optimizing the initial state of the quantum system and the reflection axis of the diffusion operator. The initial state and the reflection axis are allowed to not coincide and thus the quantum search algorithm rotates the quantum system in a three-dimensional subspace spanned by the initial state, the reflection axis, and the search target state in general. The number of oracle calls is minimized by a variational method, and formal results are obtained with the assumption of low failure probability. The results show that for a nonuniform a priori distribution of the database elements, the number of oracle calls can be significantly reduced given a small decrease in the success probability of the quantum search algorithm, leading to a lower average query complexity to find the solution of the search problem. The results are applied to a simple but nontrivial database model with two-value a priori probabilities to show the power of the optimized quantum search algorithm. The paper concludes with a discussion about the generalization to higher-order results that allows for a larger failure probability for the quantum search algorithm.
Using quantum algorithms to carry out ML tasks is what is known as Quantum Machine Learning (QML) and the methods developed within this field have the potential to outperform their classical counterparts in solving certain learning problems. The development of the field is partly dependent on that of a functional quantum random access memory (QRAM), called for by some of the algorithms devised. Such a device would store data in a superposition and could then be queried when algorithms require it, similarly to its classical counterpart, allowing for efficient data access. Taking an axiomatic approach to QRAM, this thesis provides the main considerations, assumptions and results regarding QRAM and yields a QRAM handbook and comprehensive introduction to the literature pertaining to it.
Quantum machine learning is one of the most promising applications of a full-scale quantum computer. Over the past few years, many quantum machine learning algorithms have been proposed that can potentially offer considerable speedups over the corresponding classical algorithms. In this paper, we introduce q-means, a new quantum algorithm for clustering which is a canonical problem in unsupervised machine learning. The q-means algorithm has convergence and precision guarantees similar to k-means, and it outputs with high probability a good approximation of the k cluster centroids like the classical algorithm. Given a dataset of Nd-dimensional vectors vi (seen as a matrix V∈RN×d) stored in QRAM, the running time of q-means is O(kdδ2ηκ(V)(μ(V)+kδη)+k2δ2η1.5κ(V)μ(V)) per iteration, where κ(V) is the condition number, μ(V) is a parameter that appears in quantum linear algebra procedures and η=maxi∣∣vi∣∣2. For a natural notion of well-clusterable datasets, the running time becomes O(k2dδ3η2.5+k2.5δ3η2) per iteration, which is linear in the number of features d, and polynomial in the rank k, the maximum square norm η and the error parameter δ. Both running times are only polylogarithmic in the number of datapoints N. Our algorithm provides substantial savings compared to the classical k-means algorithm that runs in time O(kdN) per iteration, particularly for the case of large datasets.
Quantum machine learning is one of the most promising applications of a full-scale quantum computer. Over the past few years, many quantum machine learning algorithms have been proposed that can potentially offer considerable speedups over the corresponding classical algorithms. In this paper, we introduce q-means, a new quantum algorithm for clustering which is a canonical problem in unsupervised machine learning. The q-means algorithm has convergence and precision guarantees similar to k-means, and it outputs with high probability a good approximation of the k cluster centroids like the classical algorithm. Given a dataset of Nd-dimensional vectors vi (seen as a matrix V∈RN×d) stored in QRAM, the running time of q-means is O(kdδ2ηκ(V)(μ(V)+kδη)+k2δ2η1.5κ(V)μ(V)) per iteration, where κ(V) is the condition number, μ(V) is a parameter that appears in quantum linear algebra procedures and η=maxi∣∣vi∣∣2. For a natural notion of well-clusterable datasets, the running time becomes O(k2dδ3η2.5+k2.5δ3η2) per iteration, which is linear in the number of features d, and polynomial in the rank k, the maximum square norm η and the error parameter δ. Both running times are only polylogarithmic in the number of datapoints N. Our algorithm provides substantial savings compared to the classical k-means algorithm that runs in time O(kdN) per iteration, particularly for the case of large datasets.