Kernel Method based on Non-Linear Coherent State

• URL: http://arxiv.org/abs/2007.07887v1
• Date: Wed, 15 Jul 2020 05:07:44 GMT
• Title: Kernel Method based on Non-Linear Coherent State
• Authors: Prayag Tiwari, Shahram Dehdashti, Abdul Karim Obeid, Massimo Melucci, Peter Bruza
• Abstract summary: We re-interpret the process of encoding inputs in quantum states as a non-linear feature map. Non-linear coherent states can be considered as natural generalisation of associated kernels. We study impact of geometrical properties of feature space, obtaining by non-linear coherent states, on the SVM classification task.
• Score: 10.557942353553859
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: In this paper, by mapping datasets to a set of non-linear coherent states, the process of encoding inputs in quantum states as a non-linear feature map is re-interpreted. As a result of this fact that the Radial Basis Function is recovered when data is mapped to a complex Hilbert state represented by coherent states, non-linear coherent states can be considered as natural generalisation of associated kernels. By considering the non-linear coherent states of a quantum oscillator with variable mass, we propose a kernel function based on generalized hypergeometric functions, as orthogonal polynomial functions. The suggested kernel is implemented with support vector machine on two well known datasets (make circles, and make moons) and outperforms the baselines, even in the presence of high noise. In addition, we study impact of geometrical properties of feature space, obtaining by non-linear coherent states, on the SVM classification task, by using considering the Fubini-Study metric of associated coherent states.

Related papers

• Enhancing Quantum Machine Learning: The Power of Non-Linear Optical Reproducing Kernels [5.270019792959673]
  Kerr kernels encode data into the phase and amplitude of Kerr coherent states. We present a novel feature space constructed using Kerr coherent states. We analyze various datasets ranging from Moon to breast cancer diagnostics.
  arXiv  Detail & Related papers  (2024-07-18T10:23:22Z)
• Topological spin excitations in non-Hermitian spin chains with a generalized kernel polynomial algorithm [1.054316838380053]
  We show a numerical approach to compute spectral functions of a non-Hermitian many-body system. We show that the local spectral functions reveal topological spin excitations in a non-Hermitian spin model. Our method offers an efficient way to compute local spectral functions in non-Hermitian quantum many-body models.
  arXiv  Detail & Related papers  (2022-08-12T18:00:07Z)
• Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings [97.12538243736705]
  We study reinforcement learning with function approximation for large-scale Partially Observable Decision Processes (POMDPs) Our algorithm provably scales to large-scale POMDPs.
  arXiv  Detail & Related papers  (2022-06-24T05:13:35Z)
• Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiency [111.83670279016599]
  We study reinforcement learning for partially observed decision processes (POMDPs) with infinite observation and state spaces. We make the first attempt at partial observability and function approximation for a class of POMDPs with a linear structure.
  arXiv  Detail & Related papers  (2022-04-20T21:15:38Z)
• The quantum Gaussian process state: A kernel-inspired state with quantum support data [0.0]
  We introduce the quantum Gaussian process state, motivated via a statistical inference for the wave function supported by a data set of unentangled product states. We show that this condenses down to a compact and expressive parametric form, with a variational flexibility shown to be competitive or surpassing established alternatives.
  arXiv  Detail & Related papers  (2021-11-19T18:33:24Z)
• Exact solutions of interacting dissipative systems via weak symmetries [77.34726150561087]
  We analytically diagonalize the Liouvillian of a class Markovian dissipative systems with arbitrary strong interactions or nonlinearity. This enables an exact description of the full dynamics and dissipative spectrum. Our method is applicable to a variety of other systems, and could provide a powerful new tool for the study of complex driven-dissipative quantum systems.
  arXiv  Detail & Related papers  (2021-09-27T17:45:42Z)
• Non-linear ladder operators and coherent states for the 2:1 oscillator [0.0]
  The 2:1 two-dimensional anisotropic quantum harmonic oscillator is considered and new sets of states are defined. The states generated are good candidates for the natural generalisation of the $mathfraksu(2)$ coherent states. The uncertainty relations of the defining chain of states are calculated and it is found that they admit a resolution of the identity and the spatial distribution of the wavefunction produces Lissajous figures.
  arXiv  Detail & Related papers  (2020-11-19T23:16:26Z)
• Local optimization on pure Gaussian state manifolds [63.76263875368856]
  We exploit insights into the geometry of bosonic and fermionic Gaussian states to develop an efficient local optimization algorithm. The method is based on notions of descent gradient attuned to the local geometry. We use the presented methods to collect numerical and analytical evidence for the conjecture that Gaussian purifications are sufficient to compute the entanglement of purification of arbitrary mixed Gaussian states.
  arXiv  Detail & Related papers  (2020-09-24T18:00:36Z)
• Construction of 'Support Vector' Machine Feature Spaces via Deformed Weyl-Heisenberg Algebra [0.9749560288448114]
  This paper uses deformed coherent states, based on a deformed Weyl-Heisenberg algebra that unifies the well-known SU(2), Weyl-Heisenberg, and SU(1,1) groups, through a common parameter. We show that deformed coherent states provide the theoretical foundation of a meta-kernel function, that is a kernel which in turn defines kernel functions.
  arXiv  Detail & Related papers  (2020-06-02T14:53:00Z)
• Semiparametric Nonlinear Bipartite Graph Representation Learning with Provable Guarantees [106.91654068632882]
  We consider the bipartite graph and formalize its representation learning problem as a statistical estimation problem of parameters in a semiparametric exponential family distribution. We show that the proposed objective is strongly convex in a neighborhood around the ground truth, so that a gradient descent-based method achieves linear convergence rate. Our estimator is robust to any model misspecification within the exponential family, which is validated in extensive experiments.
  arXiv  Detail & Related papers  (2020-03-02T16:40:36Z)
• Gaussian Process States: A data-driven representation of quantum many-body physics [59.7232780552418]
  We present a novel, non-parametric form for compactly representing entangled many-body quantum states. The state is found to be highly compact, systematically improvable and efficient to sample. It is also proven to be a universal approximator' for quantum states, able to capture any entangled many-body state with increasing data set size.
  arXiv  Detail & Related papers  (2020-02-27T15:54:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.