Barren plateaus preclude learning scramblers

• URL: http://arxiv.org/abs/2009.14808v3
• Date: Tue, 19 Oct 2021 04:17:10 GMT
• Title: Barren plateaus preclude learning scramblers
• Authors: Zo\"e Holmes, Andrew Arrasmith, Bin Yan, Patrick J. Coles, Andreas Albrecht and Andrew T. Sornborger
• Abstract summary: Scrambling processes rapidly spread entanglement through many-body quantum systems. We ask if quantum machine learning (QML) could be used to investigate such processes.
• Score: 2.442224099834475
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scrambling processes, which rapidly spread entanglement through many-body quantum systems, are difficult to investigate using standard techniques, but are relevant to quantum chaos and thermalization. In this Letter, we ask if quantum machine learning (QML) could be used to investigate such processes. We prove a no-go theorem for learning an unknown scrambling process with QML, showing that any variational ansatz is highly probable to have a barren plateau landscape, i.e., cost gradients that vanish exponentially in the system size. This implies that the required resources scale exponentially even when strategies to avoid such scaling (e.g., from ansatz-based barren plateaus or No-Free-Lunch theorems) are employed. Furthermore, we numerically and analytically extend our results to approximate scramblers. Hence, our work places generic limits on the learnability of unitaries when lacking prior information.

Related papers

• Does provable absence of barren plateaus imply classical simulability? Or, why we need to rethink variational quantum computing [0.0]
  We ask: Can the structure that allows one to avoid barren plateaus also be leveraged to efficiently simulate the loss classically? We present strong evidence that commonly used models with provable absence of barren plateaus are also classically simulable. Our analysis sheds serious doubt on the non-classicality of the information processing capabilities of parametrized quantum circuits for barren plateau-free landscapes.
  arXiv  Detail & Related papers  (2023-12-14T16:54:57Z)
• Unifying (Quantum) Statistical and Parametrized (Quantum) Algorithms [65.268245109828]
  We take inspiration from Kearns' SQ oracle and Valiant's weak evaluation oracle. We introduce an extensive yet intuitive framework that yields unconditional lower bounds for learning from evaluation queries.
  arXiv  Detail & Related papers  (2023-10-26T18:23:21Z)
• Tight and Efficient Gradient Bounds for Parameterized Quantum Circuits [7.0379869298557844]
  Training a parameterized model largely depends on the landscape of the underlying loss function. We show that these bounds, as well as the variance of the loss itself, can be estimated efficiently and classically-versa--providing practical tools to study the loss landscapes of VQA models. This insight has direct implications for hybrid Quantum Generative Adrial Networks (qGANs), a generative model that can be reformulated as a VQA with an observable composed of local and global terms.
  arXiv  Detail & Related papers  (2023-09-22T07:38:13Z)
• Free Fermion Distributions Are Hard to Learn [55.2480439325792]
  We establish the hardness of this task in the particle number non-preserving case. We give an information theoretical hardness result for the general task of learning from expectation values. In particular, we give a computational hardness result based on the assumption for learning the probability density function.
  arXiv  Detail & Related papers  (2023-06-07T18:51:58Z)
• Complexity-Theoretic Limitations on Quantum Algorithms for Topological Data Analysis [59.545114016224254]
  Quantum algorithms for topological data analysis seem to provide an exponential advantage over the best classical approach. We show that the central task of TDA -- estimating Betti numbers -- is intractable even for quantum computers. We argue that an exponential quantum advantage can be recovered if the input data is given as a specification of simplices.
  arXiv  Detail & Related papers  (2022-09-28T17:53:25Z)
• Scalable approach to many-body localization via quantum data [69.3939291118954]
  Many-body localization is a notoriously difficult phenomenon from quantum many-body physics. We propose a flexible neural network based learning approach that circumvents any computationally expensive step. Our approach can be applied to large-scale quantum experiments to provide new insights into quantum many-body physics.
  arXiv  Detail & Related papers  (2022-02-17T19:00:09Z)
• Quantum verification and estimation with few copies [63.669642197519934]
  The verification and estimation of large entangled systems represents one of the main challenges in the employment of such systems for reliable quantum information processing. This review article presents novel techniques focusing on a fixed number of resources (sampling complexity) and thus prove suitable for systems of arbitrary dimension. Specifically, a probabilistic framework requiring at best only a single copy for entanglement detection is reviewed, together with the concept of selective quantum state tomography.
  arXiv  Detail & Related papers  (2021-09-08T18:20:07Z)
• Quantum Generative Training Using R\'enyi Divergences [0.22559617939136506]
  Quantum neural networks (QNNs) are a framework for creating quantum algorithms. A major challenge in QNN development is a concentration of measure phenomenon known as a barren plateau. We show that an unbounded loss function can circumvent the existing no-go results.
  arXiv  Detail & Related papers  (2021-06-17T14:50:53Z)
• Diagnosing Barren Plateaus with Tools from Quantum Optimal Control [0.0]
  Variational Quantum Algorithms (VQAs) have received considerable attention due to their potential for achieving near-term quantum advantage. One known scaling result for VQAs is barren plateaus, where certain circumstances lead to exponentially vanishing gradients. We employ tools from quantum optimal control to develop a framework that can diagnose the presence or absence of barren plateaus for problem-inspired ansatzes.
  arXiv  Detail & Related papers  (2021-05-29T21:36:24Z)
• Entanglement Devised Barren Plateau Mitigation [1.382143546774115]
  We implicate random entanglement as the source of barren plateaus and characterize them in terms of many-body entanglement dynamics. We propose and demonstrate a number of barren plateau ameliorating techniques. We find that entanglement limiting, both automatic and engineered, is a hallmark of high-accuracy training.
  arXiv  Detail & Related papers  (2020-12-22T17:49:38Z)
• On estimating the entropy of shallow circuit outputs [49.1574468325115]
  Estimating the entropy of probability distributions and quantum states is a fundamental task in information processing. We show that entropy estimation for distributions or states produced by either log-depth circuits or constant-depth circuits with gates of bounded fan-in and unbounded fan-out is at least as hard as the Learning with Errors problem.
  arXiv  Detail & Related papers  (2020-02-27T15:32:08Z)

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.