Quantum algorithms for supervised and unsupervised machine learning
read the original abstract
Machine-learning tasks frequently involve problems of manipulating and classifying large numbers of vectors in high-dimensional spaces. Classical algorithms for solving such problems typically take time polynomial in the number of vectors and the dimension of the space. Quantum computers are good at manipulating high-dimensional vectors in large tensor product spaces. This paper provides supervised and unsupervised quantum machine learning algorithms for cluster assignment and cluster finding. Quantum machine learning can take time logarithmic in both the number of vectors and their dimension, an exponential speed-up over classical algorithms.
This paper has not been read by Pith yet.
Forward citations
Cited by 16 Pith papers
-
Filtered Spectral Projection for Quantum Principal Component Analysis
FSPA is an optimal quantum spectral projection primitive for qPCA with tight oracle complexity O((log(1/ε)+log(1/|a1|^2))/log(λ1/λ2)) and exponential copy-complexity advantage over classical methods.
-
New aspects of quantum topological data analysis: Betti number estimation, and testing and tracking of homology and cohomology classes
Quantum algorithms achieve polylogarithmic complexity for Betti number estimation and homology testing via block-encoded Laplacians and cohomological projections, claiming exponential speedups under sparsity assumptions.
-
QLAM: A Quantum Long-Attention Memory Approach to Long-Sequence Token Modeling
QLAM extends state-space models with quantum superposition in the hidden state for linear-time long-sequence modeling and reports consistent gains over RNN and transformer baselines on sequential image tasks.
-
Physics inspired quantum algorithm for QCD splitting functions
A modular two-qubit quantum circuit primitive is built to reproduce QCD gluon-splitting entanglement via concurrence, with parameters fitted to LHC data and validated on hardware for three-prong jets.
-
Physics inspired quantum algorithm for QCD splitting functions
A modular two-qubit quantum circuit is constructed to encode the concurrence of helicity entanglement in pure-gluon splitting, with parameters calibrated to LHC jet data so that composed circuits reproduce experimenta...
-
Quantum End-to-End Learning for Contextual Combinatorial Optimization
QEL is the first quantum end-to-end learning framework for contextual combinatorial optimization using QAOA with a context re-uploading phase-separator, achieving competitive performance with fewer parameters.
-
Bridge the Gap between Classical and Quantum Neural Networks with Residual Connections
HQRN creates an exact functional match to classical residual networks on basis inputs while using quantum correlations for better performance on mixed states in digit recognition and entanglement classification.
-
Divide et impera: hybrid multinomial classifiers from quantum binary models
Binary decision trees enable cost-effective multinomial classifiers from quantum binary models, matching other methods' accuracy with at most logarithmic overhead in the number of classes.
-
Hybrid Quantum-Classical Algorithm for Hamiltonian Simulation
Hybrid algorithm classically diagonalizes Hamiltonian tensor factors to construct block-encodings for quantum simulation via QSVD, with extensions for commuting time-dependent cases.
-
A resource-efficient quantum-walker Quantum RAM
Proposes a quantum-walker qRAM on a single binary tree using local operations that reduces resources while preserving optimal query complexity.
-
Hybrid quantum-classical framework for Betti number estimation with applications to topological data analysis
Hybrid quantum-classical method for Betti number estimation that combines classical simplex enumeration with quantum processing and claims polynomial-to-exponential speedups over existing quantum algorithms at the cos...
-
PINNACLE: An Open-Source Computational Framework for Classical and Quantum PINNs
PINNACLE is an open-source framework for classical and quantum PINNs that supplies modular training methods and benchmarks showing high sensitivity to architecture choices plus parameter-efficiency gains in some hybri...
-
Quantum Spectral Clustering: Comparing Parameterized and Neuromorphic Quantum Kernels
Quantum neuromorphic kernels outperform parameterized quantum kernels on low-dimensional datasets like Iris but underperform on high-dimensional SDSS data in spectral clustering tasks.
-
Machine learning methods in quantum computing theory
Authors present a multiclass tree tensor network algorithm demonstrated on IBM quantum processor and a neural network approach for noise-robust quantum state tomography.
-
Parallel Multi-Circuit Quantum Feature Fusion in Hybrid Quantum-Classical Convolutional Neural Networks for Breast Tumor Classification
A parameter-matched hybrid QCNN fusing classical features with amplitude-encoding and angle-encoding 4-qubit VQCs achieves statistically significant accuracy gains over a classical CNN on BreastMNIST (Wilcoxon p=0.031...
-
A Quantum Algorithm for Finding $k$-Minima
Quantum algorithm for k-minima with O(sqrt(k N)) query complexity via threshold search and generalized amplitude amplification.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.