arXiv subjects

Evan Peters

Publications and source records attributed to Evan Peters.

13 recordsLinked to original sources

arXiv2026

Spectral Born machines: classically trainable quantum generative models for discrete data

We present \emph{spectral Born machines}, a class of quantum generative models that results from viewing and generalizing the class of IQP Born machines through the lens of group Fourier analysis. These quantum models exploit the quantum Fourier transform to create an inductive bias that make them naturally suited to learning integer-structured data, while remaining classically hard to sample from in general. Similar to IQP Born machines, spectral Born machines can be trained efficiently at scale on classical hardware via a maximum mean discrepancy loss based on graph spectral analysis, which we make available in a new \emph{tcdq} module of the PennyLane software platform. In numerical experiments, we show how the spectral bias of the model leads to significantly reduced parameter counts compared to unstructured approaches, and demonstrate the scalability of the software by training a 190-qubit model with over 1 million parameters to successfully learn a distribution of 93 nucleotide-long ribosomal RNA. Our results suggest that highly over-parameterized spectral Born machines may be immune to overfitting, even in strongly data-scarce regimes.

quant-ph↗

arXiv2026

Spectral methods: crucial for machine learning, natural for quantum computers?

This article presents an argument for why quantum computers could unlock new methods for machine learning. We argue that spectral methods, in particular those that learn, regularise, or otherwise manipulate the Fourier spectrum of a machine learning model, are often natural for quantum computers. For example, if a generative machine learning model is represented by a quantum state, the Quantum Fourier Transform allows us to manipulate the Fourier spectrum of the state using the entire toolbox of quantum routines, an operation that is usually prohibitive for classical models. At the same time, spectral methods are surprisingly fundamental to machine learning: A spectral bias has recently been hypothesised to be the core principle behind the success of deep learning; support vector machines have been known for decades to regularise in Fourier space, and convolutional neural nets build filters in the Fourier space of images. Could, then, quantum computing open fundamentally different, much more direct and resource-efficient ways to design the spectral properties of a model? We discuss this potential in detail here, hoping to stimulate a direction in quantum machine learning research that puts the question of ``why quantum?'' first.

quant-ph↗

arXiv2026

Trapped by simplicity: When Transformers fail to learn from noisy features

Noise is ubiquitous in data used to train large language models, but it is not well understood whether these models are able to correctly generalize to inputs generated without noise. Here, we study noise-robust learning: are transformers trained on data with noisy features able to find a target function that correctly predicts labels for noiseless features? We show that transformers succeed at noise-robust learning for a selection of $k$-sparse parity and majority functions, compared to LSTMs which fail at this task for even modest feature noise. However, we find that transformers typically fail at noise-robust learning of random $k$-juntas, especially when the boolean sensitivity of the optimal solution is smaller than that of the target function. We argue that this failure is due to a combination of two factors: transformers' bias toward simpler functions, combined with an observation that the optimal function for noise-robust learning typically has lower sensitivity than the target function for random boolean functions. We test this hypothesis by exploiting transformers' simplicity bias to trap them in an incorrect solution, but show that transformers can escape this trap by training with an additional loss term penalizing high-sensitivity solutions. Overall, we find that transformers are particularly ineffective for learning boolean functions in the presence of feature noise.

cs.LG↗

arXiv2025

Importance sampling for data-driven decoding of quantum error-correcting codes

Data-driven decoding (DDD) - learning to decode syndromes of (quantum) error-correcting codes by learning from data - can be a difficult problem due to several atypical and poorly understood properties of the training data. We introduce a theory of example importance that clarifies these unusual aspects of DDD: For instance, we show that DDD of a simple error-correcting code is equivalent to a noisy, imbalanced binary classification problem. We show that an existing importance sampling technique of training neural decoders on data generated with higher error rates introduces a tradeoff between class imbalance and label noise. We apply this technique to show robust improvements in the accuracy of neural network decoders trained on syndromes sampled at higher error rates, and provide heuristic arguments for finding an optimal error rate for training data. We extend these analyses to decoding quantum codes involving multiple rounds of syndrome measurements, suggesting broad applicability of both example importance and turning the knob for improving experimentally relevant data-driven decoders.

quant-ph↗

arXiv2024

On the coherent extension of some Fano-type learning bounds

Information theory provides tools to predict the performance of a learning algorithm on a given dataset. For instance, the accuracy of learning an unknown parameter can be upper bounded by reducing the learning task to hypothesis testing for a discrete random variable, with Fano's inequality then stating that a small conditional entropy between a learner's observations and the unknown parameter is necessary for successful estimation. This work first extends this relationship by demonstrating that a small conditional entropy is also sufficient for successful learning, thereby establishing an information-theoretic lower bound on the accuracy of a learner. This connection between information theory and learning suggests that we might similarly apply quantum information theory to characterize learning tasks involving quantum systems. Observing that the fidelity of a finite-dimensional quantum system with a maximally entangled state (the singlet fraction) generalizes the success probability for estimating a discrete random variable, we introduce an entanglement manipulation task for infinite-dimensional quantum systems that similarly generalizes classical learning. We derive information-theoretic bounds for succeeding at this task in terms of the maximal singlet fraction of an appropriate finite-dimensional discretization. As classical learning is recovered as a special case of this task, our analysis suggests a deeper relationship at the interface of learning, entanglement, and information.

quant-ph↗

arXiv2022

Generalization despite overfitting in quantum machine learning models

The widespread success of deep neural networks has revealed a surprise in classical machine learning: very complex models often generalize well while simultaneously overfitting training data. This phenomenon of benign overfitting has been studied for a variety of classical models with the goal of better understanding the mechanisms behind deep learning. Characterizing the phenomenon in the context of quantum machine learning might similarly improve our understanding of the relationship between overfitting, overparameterization, and generalization. In this work, we provide a characterization of benign overfitting in quantum models. To do this, we derive the behavior of a classical interpolating Fourier features models for regression on noisy signals, and show how a class of quantum models exhibits analogous features, thereby linking the structure of quantum circuits (such as data-encoding and state preparation operations) to overparameterization and overfitting in quantum models. We intuitively explain these features according to the ability of the quantum model to interpolate noisy data with locally "spiky" behavior and provide a concrete demonstration example of benign overfitting.

quant-ph↗

arXiv2022

Bandwidth Enables Generalization in Quantum Kernel Models

Quantum computers are known to provide speedups over classical state-of-the-art machine learning methods in some specialized settings. For example, quantum kernel methods have been shown to provide an exponential speedup on a learning version of the discrete logarithm problem. Understanding the generalization of quantum models is essential to realizing similar speedups on problems of practical interest. Recent results demonstrate that generalization is hindered by the exponential size of the quantum feature space. Although these results suggest that quantum models cannot generalize when the number of qubits is large, in this paper we show that these results rely on overly restrictive assumptions. We consider a wider class of models by varying a hyperparameter that we call quantum kernel bandwidth. We analyze the large-qubit limit and provide explicit formulas for the generalization of a quantum model that can be solved in closed form. Specifically, we show that changing the value of the bandwidth can take a model from provably not being able to generalize to any target function to good generalization for well-aligned targets. Our analysis shows how the bandwidth controls the spectrum of the kernel integral operator and thereby the inductive bias of the model. We demonstrate empirically that our theory correctly predicts how varying the bandwidth affects generalization of quantum models on challenging datasets, including those far outside our theoretical assumptions. We discuss the implications of our results for quantum advantage in machine learning.

quant-ph↗

arXiv2022

Qubit assignment using time reversal

As the number of qubits available on noisy quantum computers grows, it will become necessary to efficiently select a subset of physical qubits to use in a quantum computation. For any given quantum program and device there are many ways to assign physical qubits for execution of the program, and assignments will differ in performance due to the variability in quality across qubits and entangling operations on a single device. Evaluating the performance of each assignment using fidelity estimation introduces significant experimental overhead and will be infeasible for many applications, while relying on standard device benchmarks provides incomplete information about the performance of any specific program. Furthermore, the number of possible assignments grows combinatorially in the number of qubits on the device and in the program, motivating the use of heuristic optimization techniques. We approach this problem using simulated annealing with a cost function based on the Loschmidt Echo, a diagnostic that measures the reversibility of a quantum process. We provide theoretical justification for this choice of cost function by demonstrating that the optimal qubit assignment coincides with the optimal qubit assignment based on state fidelity in the weak error limit, and we provide experimental justification using diagnostics performed on Google's superconducting qubit devices. We then establish the performance of simulated annealing for qubit assignment using classical simulations of noisy devices as well as optimization experiments performed on a quantum processor. Our results demonstrate that the use of Loschmidt Echoes and simulated annealing provides a scalable and flexible approach to optimizing qubit assignment on near-term hardware.

quant-ph↗

arXiv2021

Simulations of Quantum Circuits with Approximate Noise using qsim and Cirq

We introduce multinode quantum trajectory simulations with qsim, an open source high performance simulator of quantum circuits. qsim can be used as a backend of Cirq, a Python software library for writing quantum circuits. We present a novel delayed inner product algorithm for quantum trajectories which can result in an order of magnitude speedup for low noise simulation. We also provide tools to use this framework in Google Cloud Platform, with high performance virtual machines in a single mode or multinode setting. Multinode configurations are well suited to simulate noisy quantum circuits with quantum trajectories. Finally, we introduce an approximate noise model for Google's experimental quantum computing platform and compare the results of noisy simulations with experiments for several quantum algorithms on Google's Quantum Computing Service.

quant-ph↗

arXiv2021

Large scale multi-node simulations of $\mathbb{Z}_2$ gauge theory quantum circuits using Google Cloud Platform

Simulating quantum field theories on a quantum computer is one of the most exciting fundamental physics applications of quantum information science. Dynamical time evolution of quantum fields is a challenge that is beyond the capabilities of classical computing, but it can teach us important lessons about the fundamental fabric of space and time. Whether we may answer scientific questions of interest using near-term quantum computing hardware is an open question that requires a detailed simulation study of quantum noise. Here we present a large scale simulation study powered by a multi-node implementation of qsim using the Google Cloud Platform. We additionally employ newly-developed GPU capabilities in qsim and show how Tensor Processing Units -- Application-specific Integrated Circuits (ASICs) specialized for Machine Learning -- may be used to dramatically speed up the simulation of large quantum circuits. We demonstrate the use of high performance cloud computing for simulating $\mathbb{Z}_2$ quantum field theories on system sizes up to 36 qubits. We find this lattice size is not able to simulate our problem and observable combination with sufficient accuracy, implying more challenging observables of interest for this theory are likely beyond the reach of classical computation using exact circuit simulation.

quant-ph↗

arXiv2021

Perturbative readout error mitigation for near term quantum computers

Readout errors on near-term quantum computers can introduce significant error to the empirical probability distribution sampled from the output of a quantum circuit. These errors can be mitigated by classical postprocessing given the access of an experimental \emph{response matrix} that describes the error associated with measurement of each computational basis state. However, the resources required to characterize a complete response matrix and to compute the corrected probability distribution scale exponentially in the number of qubits $n$. In this work, we modify standard matrix inversion techniques using two perturbative approximations with significantly reduced complexity and bounded error when the likelihood of high order bitflip events is strongly suppressed. Given a characteristic error rate $q$, our first method recovers the probability of the all-zeros bitstring $p_0$ by sampling only a small subspace of the response matrix before inverting readout error resulting in a relative speedup of $\text{poly}\left(2^{n} / \big(\begin{smallmatrix} n \\ w \end{smallmatrix}\big)\right)$, which we motivate using a simplified error model for which the approximation incurs only $O(q^w)$ error for some integer $w$. We then provide a generalized technique to efficiently recover full output distributions with $O(q^w)$ error in the perturbative limit. These approximate techniques for readout error correction may greatly accelerate near term quantum computing applications.

quant-ph↗

arXiv2021

Machine learning of high dimensional data on a noisy quantum processor

We present a quantum kernel method for high-dimensional data analysis using Google's universal quantum processor, Sycamore. This method is successfully applied to the cosmological benchmark of supernova classification using real spectral features with no dimensionality reduction and without vanishing kernel elements. Instead of using a synthetic dataset of low dimension or pre-processing the data with a classical machine learning algorithm to reduce the data dimension, this experiment demonstrates that machine learning with real, high dimensional data is possible using a quantum processor; but it requires careful attention to shot statistics and mean kernel element size when constructing a circuit ansatz. Our experiment utilizes 17 qubits to classify 67 dimensional data - significantly higher dimensionality than the largest prior quantum kernel experiments - resulting in classification accuracy that is competitive with noiseless simulation and comparable classical techniques.

quant-ph↗

arXiv2020

TensorFlow Quantum: A Software Framework for Quantum Machine Learning

We introduce TensorFlow Quantum (TFQ), an open source library for the rapid prototyping of hybrid quantum-classical models for classical or quantum data. This framework offers high-level abstractions for the design and training of both discriminative and generative quantum models under TensorFlow and supports high-performance quantum circuit simulators. We provide an overview of the software architecture and building blocks through several examples and review the theory of hybrid quantum-classical neural networks. We illustrate TFQ functionalities via several basic applications including supervised learning for quantum classification, quantum control, simulating noisy quantum circuits, and quantum approximate optimization. Moreover, we demonstrate how one can apply TFQ to tackle advanced quantum learning tasks including meta-learning, layerwise learning, Hamiltonian learning, sampling thermal states, variational quantum eigensolvers, classification of quantum phase transitions, generative adversarial networks, and reinforcement learning. We hope this framework provides the necessary tools for the quantum computing and machine learning research communities to explore models of both natural and artificial quantum systems, and ultimately discover new quantum algorithms which could potentially yield a quantum advantage.

quant-ph↗