Quark: A Gradient-Free Quantum Learning Framework for Classification Tasks

• URL: http://arxiv.org/abs/2210.01311v1
• Date: Sun, 2 Oct 2022 19:23:35 GMT
• Title: Quark: A Gradient-Free Quantum Learning Framework for Classification Tasks
• Authors: Zhihao Zhang, Zhuoming Chen, Heyang Huang, Zhihao Jia
• Abstract summary: We introduce Quark, a gradient quantum learning framework that optimize quantum ML models using quantum optimization. Quark does not rely on gradient-free computation and avoids frequent classical-quantum interactions.
• Score: 2.6763498831034034
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As more practical and scalable quantum computers emerge, much attention has been focused on realizing quantum supremacy in machine learning. Existing quantum ML methods either (1) embed a classical model into a target Hamiltonian to enable quantum optimization or (2) represent a quantum model using variational quantum circuits and apply classical gradient-based optimization. The former method leverages the power of quantum optimization but only supports simple ML models, while the latter provides flexibility in model design but relies on gradient calculation, resulting in barren plateau (i.e., gradient vanishing) and frequent classical-quantum interactions. To address the limitations of existing quantum ML methods, we introduce Quark, a gradient-free quantum learning framework that optimizes quantum ML models using quantum optimization. Quark does not rely on gradient computation and therefore avoids barren plateau and frequent classical-quantum interactions. In addition, Quark can support more general ML models than prior quantum ML methods and achieves a dataset-size-independent optimization complexity. Theoretically, we prove that Quark can outperform classical gradient-based methods by reducing model query complexity for highly non-convex problems; empirically, evaluations on the Edge Detection and Tiny-MNIST tasks show that Quark can support complex ML models and significantly reduce the number of measurements needed for discovering near-optimal weights for these tasks.

Related papers

• Efficient Learning for Linear Properties of Bounded-Gate Quantum Circuits [63.733312560668274]
  Given a quantum circuit containing d tunable RZ gates and G-d Clifford gates, can a learner perform purely classical inference to efficiently predict its linear properties? We prove that the sample complexity scaling linearly in d is necessary and sufficient to achieve a small prediction error, while the corresponding computational complexity may scale exponentially in d. We devise a kernel-based learning model capable of trading off prediction error and computational complexity, transitioning from exponential to scaling in many practical settings.
  arXiv  Detail & Related papers  (2024-08-22T08:21:28Z)
• Explicit quantum surrogates for quantum kernel models [0.6834295298053009]
  We propose a quantum-classical hybrid algorithm to create an explicit quantum surrogate (EQS) for trained implicit models. This involves diagonalizing an observable from the implicit model and constructing a corresponding quantum circuit. The EQS framework reduces prediction costs, mitigates barren plateau issues, and combines the strengths of both QML approaches.
  arXiv  Detail & Related papers  (2024-08-06T07:15:45Z)
• Parallel Quantum Computing Simulations via Quantum Accelerator Platform Virtualization [44.99833362998488]
  We present a model for parallelizing simulation of quantum circuit executions. The model can take advantage of its backend-agnostic features, enabling parallel quantum circuit execution over any target backend.
  arXiv  Detail & Related papers  (2024-06-05T17:16:07Z)
• Truncation technique for variational quantum eigensolver for Molecular Hamiltonians [0.0]
  variational quantum eigensolver (VQE) is one of the most promising quantum algorithms for noisy quantum devices. We propose a physically intuitive truncation technique that starts the optimization procedure with a truncated Hamiltonian. This strategy allows us to reduce the required number of evaluations for the expectation value of Hamiltonian on a quantum computer.
  arXiv  Detail & Related papers  (2024-02-02T18:45:12Z)
• Ansatz-Agnostic Exponential Resource Saving in Variational Quantum Algorithms Using Shallow Shadows [5.618657159109373]
  Variational Quantum Algorithms (VQA) have been identified as a promising candidate for the demonstration of near-term quantum advantage. We present a protocol based on shallow shadows that achieves similar levels of savings for almost any shallow ansatz studied in the literature. We show that two important applications in quantum information for which VQAs can be a powerful option, namely variational quantum state preparation and variational quantum circuit synthesis.
  arXiv  Detail & Related papers  (2023-09-09T11:00:39Z)
• Adapting Pre-trained Language Models for Quantum Natural Language Processing [33.86835690434712]
  We show that pre-trained representation can bring 50% to 60% increases to the capacity of end-to-end quantum models. On quantum simulation experiments, the pre-trained representation can bring 50% to 60% increases to the capacity of end-to-end quantum models.
  arXiv  Detail & Related papers  (2023-02-24T14:59:02Z)
• Provably efficient variational generative modeling of quantum many-body systems via quantum-probabilistic information geometry [3.5097082077065003]
  We introduce a generalization of quantum natural gradient descent to parameterized mixed states. We also provide a robust first-order approximating algorithm, Quantum-Probabilistic Mirror Descent. Our approaches extend previously sample-efficient techniques to allow for flexibility in model choice.
  arXiv  Detail & Related papers  (2022-06-09T17:58:15Z)
• An Introduction to Quantum Machine Learning for Engineers [36.18344598412261]
  Quantum machine learning is emerging as a dominant paradigm to program gate-based quantum computers. This book provides a self-contained introduction to quantum machine learning for an audience of engineers with a background in probability and linear algebra.
  arXiv  Detail & Related papers  (2022-05-11T12:10:52Z)
• Quantum algorithms for quantum dynamics: A performance study on the spin-boson model [68.8204255655161]
  Quantum algorithms for quantum dynamics simulations are traditionally based on implementing a Trotter-approximation of the time-evolution operator. variational quantum algorithms have become an indispensable alternative, enabling small-scale simulations on present-day hardware. We show that, despite providing a clear reduction of quantum gate cost, the variational method in its current implementation is unlikely to lead to a quantum advantage.
  arXiv  Detail & Related papers  (2021-08-09T18:00:05Z)
• Variational Quantum Optimization with Multi-Basis Encodings [62.72309460291971]
  We introduce a new variational quantum algorithm that benefits from two innovations: multi-basis graph complexity and nonlinear activation functions. Our results in increased optimization performance, two increase in effective landscapes and a reduction in measurement progress.
  arXiv  Detail & Related papers  (2021-06-24T20:16:02Z)
• Higgs analysis with quantum classifiers [0.0]
  We have developed two quantum classifier models for the $tbartH(bbarb)$ classification problem. Our results serve as a proof of concept that Quantum Machine Learning (QML) methods can have similar or better performance.
  arXiv  Detail & Related papers  (2021-04-15T18:01:51Z)

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.