Quantum-Classical Separations in Shallow-Circuit-Based Learning with and without Noises
- URL: http://arxiv.org/abs/2405.00770v1
- Date: Wed, 1 May 2024 18:00:01 GMT
- Title: Quantum-Classical Separations in Shallow-Circuit-Based Learning with and without Noises
- Authors: Zhihan Zhang, Weiyuan Gong, Weikang Li, Dong-Ling Deng,
- Abstract summary: We study quantum-classical separations between classical and quantum supervised learning models based on constant depth (i.e., shallow) circuits.
We rigorously prove that any classical neural network with bounded connectivity requires logarithmic depth to output correctly with a larger-than-exponentially-small probability.
- Score: 5.018448337319583
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We study quantum-classical separations between classical and quantum supervised learning models based on constant depth (i.e., shallow) circuits, in scenarios with and without noises. We construct a classification problem defined by a noiseless shallow quantum circuit and rigorously prove that any classical neural network with bounded connectivity requires logarithmic depth to output correctly with a larger-than-exponentially-small probability. This unconditional near-optimal quantum-classical separation originates from the quantum nonlocality property that distinguishes quantum circuits from their classical counterparts. We further derive the noise thresholds for demonstrating such a separation on near-term quantum devices under the depolarization noise model. We prove that this separation will persist if the noise strength is upper bounded by an inverse polynomial with respect to the system size, and vanish if the noise strength is greater than an inverse polylogarithmic function. In addition, for quantum devices with constant noise strength, we prove that no super-polynomial classical-quantum separation exists for any classification task defined by shallow Clifford circuits, independent of the structures of the circuits that specify the learning models.
Related papers
- A polynomial-time classical algorithm for noisy quantum circuits [1.2708457954150887]
We provide a-time classical algorithm for noisy quantum circuits.
Our approach is based upon the intuition that noise exponentially damps non-local correlations.
arXiv Detail & Related papers (2024-07-17T17:48:39Z) - A Quantum-Classical Collaborative Training Architecture Based on Quantum
State Fidelity [50.387179833629254]
We introduce a collaborative classical-quantum architecture called co-TenQu.
Co-TenQu enhances a classical deep neural network by up to 41.72% in a fair setting.
It outperforms other quantum-based methods by up to 1.9 times and achieves similar accuracy while utilizing 70.59% fewer qubits.
arXiv Detail & Related papers (2024-02-23T14:09:41Z) - Classically computing performance bounds on depolarized quantum circuits [0.0]
We compute a certifiable lower bound on the minimum energy attainable by the output state of a quantum circuit in the presence of depolarizing noise.
We provide theoretical and numerical evidence that this approach can provide circuit-architecture bounds dependent on the performance of noisy quantum circuits.
arXiv Detail & Related papers (2023-06-28T16:41:56Z) - Classical Capacity of Arbitrarily Distributed Noisy Quantum Channels [11.30845610345922]
We study the impact of a mixture of classical and quantum noise on an arbitrary quantum channel carrying classical information.
We formulate the achievable channel capacity over an arbitrary distributed quantum channel in presence of the mixed noise.
arXiv Detail & Related papers (2023-06-28T11:14:12Z) - The Quantum Path Kernel: a Generalized Quantum Neural Tangent Kernel for
Deep Quantum Machine Learning [52.77024349608834]
Building a quantum analog of classical deep neural networks represents a fundamental challenge in quantum computing.
Key issue is how to address the inherent non-linearity of classical deep learning.
We introduce the Quantum Path Kernel, a formulation of quantum machine learning capable of replicating those aspects of deep machine learning.
arXiv Detail & Related papers (2022-12-22T16:06:24Z) - Quantum emulation of the transient dynamics in the multistate
Landau-Zener model [50.591267188664666]
We study the transient dynamics in the multistate Landau-Zener model as a function of the Landau-Zener velocity.
Our experiments pave the way for more complex simulations with qubits coupled to an engineered bosonic mode spectrum.
arXiv Detail & Related papers (2022-11-26T15:04:11Z) - Certified Robustness of Quantum Classifiers against Adversarial Examples
through Quantum Noise [68.1992787416233]
We show that adding quantum random rotation noise can improve robustness in quantum classifiers against adversarial attacks.
We derive a certified robustness bound to enable quantum classifiers to defend against adversarial examples.
arXiv Detail & Related papers (2022-11-02T05:17:04Z) - Experimental violations of Leggett-Garg's inequalities on a quantum
computer [77.34726150561087]
We experimentally observe the violations of Leggett-Garg-Bell's inequalities on single and multi-qubit systems.
Our analysis highlights the limits of nowadays quantum platforms, showing that the above-mentioned correlation functions deviate from theoretical prediction as the number of qubits and the depth of the circuit grow.
arXiv Detail & Related papers (2021-09-06T14:35:15Z) - Chaos in the quantum Duffing oscillator in the semiclassical regime
under parametrized dissipation [0.0]
We study the quantum dissipative Duffing oscillator across a range of system sizes and environmental couplings.
We quantify the system sizes where quantum dynamics cannot be simulated using semiclassical or noise-added classical approximations.
Our findings generalize the previous surprising result that classically regular orbits can have the greatest quantum-classical differences in the semiclassical regime.
arXiv Detail & Related papers (2020-10-30T22:03:02Z) - Limitations of optimization algorithms on noisy quantum devices [0.0]
We present a transparent way of comparing classical algorithms to quantum ones running on near-term quantum devices.
Our approach is based on the combination of entropic inequalities that determine how fast the quantum state converges to the fixed point of the noise model.
arXiv Detail & Related papers (2020-09-11T17:07:26Z) - Quantum noise protects quantum classifiers against adversaries [120.08771960032033]
Noise in quantum information processing is often viewed as a disruptive and difficult-to-avoid feature, especially in near-term quantum technologies.
We show that by taking advantage of depolarisation noise in quantum circuits for classification, a robustness bound against adversaries can be derived.
This is the first quantum protocol that can be used against the most general adversaries.
arXiv Detail & Related papers (2020-03-20T17:56:14Z)
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.