Quantum Conformal Prediction for Reliable Uncertainty Quantification in Quantum Machine Learning

• URL: http://arxiv.org/abs/2304.03398v3
• Date: Sun, 22 Oct 2023 19:51:31 GMT
• Title: Quantum Conformal Prediction for Reliable Uncertainty Quantification in Quantum Machine Learning
• Authors: Sangwoo Park, Osvaldo Simeone
• Abstract summary: Quantum models implement implicit probabilistic predictors that produce multiple random decisions for each input through measurement shots. This paper proposes to leverage such randomness to define prediction sets for both classification and regression that provably capture the uncertainty of the model.
• Score: 47.991114317813555
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this work, we aim at augmenting the decisions output by quantum models with "error bars" that provide finite-sample coverage guarantees. Quantum models implement implicit probabilistic predictors that produce multiple random decisions for each input through measurement shots. Randomness arises not only from the inherent stochasticity of quantum measurements, but also from quantum gate noise and quantum measurement noise caused by noisy hardware. Furthermore, quantum noise may be correlated across shots and it may present drifts in time. This paper proposes to leverage such randomness to define prediction sets for both classification and regression that provably capture the uncertainty of the model. The approach builds on probabilistic conformal prediction (PCP), while accounting for the unique features of quantum models. Among the key technical innovations, we introduce a new general class of non-conformity scores that address the presence of quantum noise, including possible drifts. Experimental results, using both simulators and current quantum computers, confirm the theoretical calibration guarantees of the proposed framework.

Related papers

• The curse of random quantum data [62.24825255497622]
  We quantify the performances of quantum machine learning in the landscape of quantum data. We find that the training efficiency and generalization capabilities in quantum machine learning will be exponentially suppressed with the increase in qubits. Our findings apply to both the quantum kernel method and the large-width limit of quantum neural networks.
  arXiv  Detail & Related papers  (2024-08-19T12:18:07Z)
• Single-shot quantum machine learning [0.3277163122167433]
  We analyze when quantum learning models can produce predictions in a near-deterministic way. We show that the degree to which a quantum learning model is near-deterministic is constrained by the distinguishability of the embedded quantum states. We conclude by showing that quantum learning models cannot be single-shot in a generic way and trainable at the same time.
  arXiv  Detail & Related papers  (2024-06-19T20:17:18Z)
• Power Characterization of Noisy Quantum Kernels [52.47151453259434]
  We show that noise may make quantum kernel methods to only have poor prediction capability, even when the generalization error is small. We provide a crucial warning to employ noisy quantum kernel methods for quantum computation.
  arXiv  Detail & Related papers  (2024-01-31T01:02:16Z)
• Practical limitations of quantum data propagation on noisy quantum processors [0.9362259192191963]
  We show that owing to the noisy nature of current quantum processors, such a quantum algorithm will require single- and two-qubit gates with very low error probability to produce reliable results. Specifically, we provide the upper bounds on how the relative error in variational parameters' propagation scales with the probability of noise in quantum hardware.
  arXiv  Detail & Related papers  (2023-06-22T17:12:52Z)
• Statistical learning on randomized data to verify quantum state k-designs [0.0]
  Random ensembles of pure states have proven to be extremely important in various aspects of quantum physics. generating a fully random ensemble is experimentally challenging but approximations are just as useful. verifying their degree of randomness can be an expensive task, similar to performing full quantum state tomography on many-body systems.
  arXiv  Detail & Related papers  (2023-05-02T14:46:28Z)
• 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)
• On Quantum Circuits for Discrete Graphical Models [1.0965065178451106]
  We provide the first method that allows one to provably generate unbiased and independent samples from general discrete factor models. Our method is compatible with multi-body interactions and its success probability does not depend on the number of variables. Experiments with quantum simulation as well as actual quantum hardware show that our method can carry out sampling and parameter learning on quantum computers.
  arXiv  Detail & Related papers  (2022-06-01T11:03:51Z)
• Noisy Quantum Kernel Machines [58.09028887465797]
  An emerging class of quantum learning machines is that based on the paradigm of quantum kernels. We study how dissipation and decoherence affect their performance. We show that decoherence and dissipation can be seen as an implicit regularization for the quantum kernel machines.
  arXiv  Detail & Related papers  (2022-04-26T09:52:02Z)
• Quantum Local Differential Privacy and Quantum Statistical Query Model [0.7673339435080445]
  Quantum statistical queries provide a theoretical framework for investigating the computational power of a learner with limited quantum resources. In this work, we establish an equivalence between quantum statistical queries and quantum differential privacy in the local model. We consider the task of quantum multi-party computation under local differential privacy.
  arXiv  Detail & Related papers  (2022-03-07T18:38:02Z)
• Quantum Random Number Generation using a Solid-State Single-Photon Source [89.24951036534168]
  Quantum random number generation (QRNG) harnesses the intrinsic randomness of quantum mechanical phenomena. We demonstrate QRNG with a quantum emitter in hexagonal boron nitride. Our results open a new avenue to the fabrication of on-chip deterministic random number generators.
  arXiv  Detail & Related papers  (2020-01-28T22:47:43Z)

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.