Universal scaling laws in quantum-probabilistic machine learning by tensor network towards interpreting representation and generalization powers

• URL: http://arxiv.org/abs/2410.09703v1
• Date: Sun, 13 Oct 2024 02:48:08 GMT
• Title: Universal scaling laws in quantum-probabilistic machine learning by tensor network towards interpreting representation and generalization powers
• Authors: Sheng-Chen Bai, Shi-Ju Ran,
• Abstract summary: This work contributes to uncovering the emergence of universal scaling laws in quantum-probabilistic ML. We take the generative tensor network (GTN) in the form of a matrix product state as an example. We show that with an untrained GTN, the negative logarithmic likelihood (NLL) $L$ generally increases linearly with the number of features.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Interpreting the representation and generalization powers has been a long-standing issue in the field of machine learning (ML) and artificial intelligence. This work contributes to uncovering the emergence of universal scaling laws in quantum-probabilistic ML. We take the generative tensor network (GTN) in the form of a matrix product state as an example and show that with an untrained GTN (such as a random TN state), the negative logarithmic likelihood (NLL) $L$ generally increases linearly with the number of features $M$, i.e., $L \simeq k M + const$. This is a consequence of the so-called ``catastrophe of orthogonality,'' which states that quantum many-body states tend to become exponentially orthogonal to each other as $M$ increases. We reveal that while gaining information through training, the linear scaling law is suppressed by a negative quadratic correction, leading to $L \simeq \beta M - \alpha M^2 + const$. The scaling coefficients exhibit logarithmic relationships with the number of training samples and the number of quantum channels $\chi$. The emergence of the quadratic correction term in NLL for the testing (training) set can be regarded as evidence of the generalization (representation) power of GTN. Over-parameterization can be identified by the deviation in the values of $\alpha$ between training and testing sets while increasing $\chi$. We further investigate how orthogonality in the quantum feature map relates to the satisfaction of quantum probabilistic interpretation, as well as to the representation and generalization powers of GTN. The unveiling of universal scaling laws in quantum-probabilistic ML would be a valuable step toward establishing a white-box ML scheme interpreted within the quantum probabilistic framework.

Related papers

• The Power of Unentangled Quantum Proofs with Non-negative Amplitudes [55.90795112399611]
  We study the power of unentangled quantum proofs with non-negative amplitudes, a class which we denote $textQMA+(2)$. In particular, we design global protocols for small set expansion, unique games, and PCP verification. We show that QMA(2) is equal to $textQMA+(2)$ provided the gap of the latter is a sufficiently large constant.
  arXiv  Detail & Related papers  (2024-02-29T01:35:46Z)
• Quantum tomography of helicity states for general scattering processes [55.2480439325792]
  Quantum tomography has become an indispensable tool in order to compute the density matrix $rho$ of quantum systems in Physics. We present the theoretical framework for reconstructing the helicity quantum initial state of a general scattering process.
  arXiv  Detail & Related papers  (2023-10-16T21:23:42Z)
• Recurrent Neural Language Models as Probabilistic Finite-state Automata [66.23172872811594]
  We study what classes of probability distributions RNN LMs can represent. We show that simple RNNs are equivalent to a subclass of probabilistic finite-state automata. These results present a first step towards characterizing the classes of distributions RNN LMs can represent.
  arXiv  Detail & Related papers  (2023-10-08T13:36:05Z)
• Exponentially improved efficient machine learning for quantum many-body states with provable guarantees [0.0]
  We provide theoretical guarantees for efficient learning of quantum many-body states and their properties, with model-independent applications. Our results provide theoretical guarantees for efficient learning of quantum many-body states and their properties, with model-independent applications.
  arXiv  Detail & Related papers  (2023-04-10T02:22:36Z)
• Learning Quantum Processes and Hamiltonians via the Pauli Transfer Matrix [0.0]
  Learning about physical systems from quantum-enhanced experiments can outperform learning from experiments in which only classical memory and processing are available. We show that a quantum memory allows to efficiently solve the following tasks. Our results highlight the power of quantum-enhanced experiments for learning highly complex quantum dynamics.
  arXiv  Detail & Related papers  (2022-12-08T18:46:06Z)
• Theory of Quantum Generative Learning Models with Maximum Mean Discrepancy [67.02951777522547]
  We study learnability of quantum circuit Born machines (QCBMs) and quantum generative adversarial networks (QGANs) We first analyze the generalization ability of QCBMs and identify their superiorities when the quantum devices can directly access the target distribution. Next, we prove how the generalization error bound of QGANs depends on the employed Ansatz, the number of qudits, and input states.
  arXiv  Detail & Related papers  (2022-05-10T08:05:59Z)
• The power of qutrits for non-adaptive measurement-based quantum computing [0.0]
  We prove that quantum correlations enable the computation of all ternary functions using the generalised qutrit Greenberger-Horne-Zeilinger (GHZ) state as a resource and at most $3n-1$ qutrits. This yields a corresponding generalised GHZ type paradox for any ternary function that LHVs cannot compute.
  arXiv  Detail & Related papers  (2022-03-23T13:41:22Z)
• A lower bound on the space overhead of fault-tolerant quantum computation [51.723084600243716]
  The threshold theorem is a fundamental result in the theory of fault-tolerant quantum computation. We prove an exponential upper bound on the maximal length of fault-tolerant quantum computation with amplitude noise.
  arXiv  Detail & Related papers  (2022-01-31T22:19:49Z)
• Generalization in quantum machine learning from few training data [4.325561431427748]
  Modern quantum machine learning (QML) methods involve variationally optimizing a parameterized quantum circuit on a training data set. We show that the generalization error of a quantum machine learning model with $T$ trainable gates at worst as $sqrtT/N$. We also show that classification of quantum states across a phase transition with a quantum convolutional neural network requires only a very small training data set.
  arXiv  Detail & Related papers  (2021-11-09T17:49:46Z)
• Deterministic and Entanglement-Efficient Preparation of Amplitude-Encoded Quantum Registers [0.533024001730262]
  A classical vector $mathbfb$ is encoded in the amplitudes of a quantum state. An arbitrary state of $Q$ qubits generally requires approximately $2Q$ entangling gates. We present a deterministic (nonvariational) algorithm that allows one to flexibly reduce the quantum resources required for state preparation.
  arXiv  Detail & Related papers  (2021-10-26T07:37:54Z)
• Quantum Gram-Schmidt Processes and Their Application to Efficient State Read-out for Quantum Algorithms [87.04438831673063]
  We present an efficient read-out protocol that yields the classical vector form of the generated state. Our protocol suits the case that the output state lies in the row space of the input matrix. One of our technical tools is an efficient quantum algorithm for performing the Gram-Schmidt orthonormal procedure.
  arXiv  Detail & Related papers  (2020-04-14T11:05:26Z)

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.