Ryan Sweke
YOU?
Author Swipe
View article: On the average-case complexity of learning output distributions of quantum circuits
On the average-case complexity of learning output distributions of quantum circuits Open
In this work, we show that learning the output distributions of brickwork random quantum circuits is average-case hard in the statistical query model. This learning model is widely used as an abstract computational model for most generic l…
View article: Wavefunction Flows: Efficient Quantum Simulation of Continuous Flow Models
Wavefunction Flows: Efficient Quantum Simulation of Continuous Flow Models Open
Flow models are a cornerstone of modern machine learning. They are generative models that progressively transform probability distributions according to learned dynamics. Specifically, they learn a continuous-time Markov process that effic…
View article: Kernel-based dequantization of variational QML without Random Fourier Features
Kernel-based dequantization of variational QML without Random Fourier Features Open
There is currently a huge effort to understand the potential and limitations of variational quantum machine learning (QML) based on the optimization of parameterized quantum circuits. Recent proposals toward dequantizing variational QML mo…
View article: New perspectives on quantum kernels through the lens of entangled tensor kernels
New perspectives on quantum kernels through the lens of entangled tensor kernels Open
Quantum kernel methods are one of the most explored approaches to quantum machine learning. However, the structural properties and inductive bias of quantum kernels are not fully understood. In this work, we introduce the notion of entangl…
View article: Potential and limitations of random Fourier features for dequantizing quantum machine learning
Potential and limitations of random Fourier features for dequantizing quantum machine learning Open
Quantum machine learning is arguably one of the most explored applications of near-term quantum devices. Much focus has been put on notions of variational quantum machine learning where (PQCs) are used as learning models. These PQC models…
View article: Dynamic parameterized quantum circuits: expressive and barren-plateau free
Dynamic parameterized quantum circuits: expressive and barren-plateau free Open
Classical optimization of parameterized quantum circuits is a widely studied methodology for the preparation of complex quantum states, as well as the solution of machine learning and optimization problems. However, it is well known that m…
View article: Interactive proofs for verifying (quantum) learning and testing
Interactive proofs for verifying (quantum) learning and testing Open
We consider the problem of testing and learning from data in the presence of resource constraints, such as limited memory or weak data access, which place limitations on the efficiency and feasibility of testing or learning. In particular,…
View article: Learning topological states from randomized measurements using variational tensor network tomography
Learning topological states from randomized measurements using variational tensor network tomography Open
Learning faithful representations of quantum states is crucial to fully characterizing the variety of many-body states created on quantum processors. While various tomographic methods such as classical shadow and MPS tomography have shown …
View article: Classical Verification of Quantum Learning
Classical Verification of Quantum Learning Open
Quantum data access and quantum processing can make certain classically intractable learning tasks feasible. However, quantum capabilities will only be available to a select few in the near future. Thus, reliable schemes that allow classic…
View article: Potential and limitations of random Fourier features for dequantizing quantum machine learning
Potential and limitations of random Fourier features for dequantizing quantum machine learning Open
Quantum machine learning is arguably one of the most explored applications of near-term quantum devices. Much focus has been put on notions of variational quantum machine learning where parameterized quantum circuits (PQCs) are used as lea…
View article: One <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline"><mml:mi>T</mml:mi></mml:math> Gate Makes Distribution Learning Hard
One Gate Makes Distribution Learning Hard Open
The task of learning a probability distribution from samples is ubiquitous across the natural sciences. The output distributions of local quantum circuits are of central importance in both quantum advantage proposals and a variety of quant…
View article: On the average-case complexity of learning output distributions of quantum circuits
On the average-case complexity of learning output distributions of quantum circuits Open
In this work, we show that learning the output distributions of brickwork random quantum circuits is average-case hard in the statistical query model. This learning model is widely used as an abstract computational model for most generic l…
View article: Superpolynomial quantum-classical separation for density modeling
Superpolynomial quantum-classical separation for density modeling Open
Density modeling is the task of learning an unknown probability density function from samples, and is one of the central problems of unsupervised machine learning. In this work, we show that there exists a density modeling problem for whic…
View article: Scalably learning quantum many-body Hamiltonians from dynamical data
Scalably learning quantum many-body Hamiltonians from dynamical data Open
Our paper on Hamiltonian learning for large quantum systems contains several numerical results. The results were produced with the differentiable-tebd package which we developed for this study. The scripts and raw output data, as well as J…
View article: Scalably learning quantum many-body Hamiltonians from dynamical data
Scalably learning quantum many-body Hamiltonians from dynamical data Open
Our paper on Hamiltonian learning for large quantum systems contains several numerical results. The results were produced with the differentiable-tebd package which we developed for this study. The scripts and raw output data, as well as J…
View article: A super-polynomial quantum-classical separation for density modelling
A super-polynomial quantum-classical separation for density modelling Open
Density modelling is the task of learning an unknown probability density function from samples, and is one of the central problems of unsupervised machine learning. In this work, we show that there exists a density modelling problem for wh…
View article: Scalably learning quantum many-body Hamiltonians from dynamical data
Scalably learning quantum many-body Hamiltonians from dynamical data Open
The physics of a closed quantum mechanical system is governed by its Hamiltonian. However, in most practical situations, this Hamiltonian is not precisely known, and ultimately all there is are data obtained from measurements on the system…
View article: A single $T$-gate makes distribution learning hard
A single $T$-gate makes distribution learning hard Open
The task of learning a probability distribution from samples is ubiquitous across the natural sciences. The output distributions of local quantum circuits form a particularly interesting class of distributions, of key importance both to qu…
View article: Transparent reporting of research-related greenhouse gas emissions\n through the scientific CO$_2$nduct initiative
Transparent reporting of research-related greenhouse gas emissions\n through the scientific CO$_2$nduct initiative Open
Estimating the greenhouse gas emissions of research-related activities is a\ncritical first step towards the design of mitigation policies and actions. Here\nwe propose and motivate a transparent framework for reporting research-related\ng…
View article: Encoding-dependent generalization bounds for parametrized quantum circuits
Encoding-dependent generalization bounds for parametrized quantum circuits Open
A large body of recent work has begun to explore the potential of parametrized quantum circuits (PQCs) as machine learning models, within the framework of hybrid quantum-classical optimization. In particular, theoretical guarantees on the …
View article: Learnability of the output distributions of local quantum circuits
Learnability of the output distributions of local quantum circuits Open
There is currently a large interest in understanding the potential advantages quantum devices can offer for probabilistic modelling. In this work we investigate, within two different oracle models, the probably approximately correct (PAC) …
View article: Effect of data encoding on the expressive power of variational quantum-machine-learning models
Effect of data encoding on the expressive power of variational quantum-machine-learning models Open
Quantum computers can be used for supervised learning by treating\nparametrised quantum circuits as models that map data inputs to predictions.\nWhile a lot of work has been done to investigate practical implications of this\napproach, man…
View article: On the Quantum versus Classical Learnability of Discrete Distributions
On the Quantum versus Classical Learnability of Discrete Distributions Open
Here we study the comparative power of classical and quantum learners for generative modelling within the Probably Approximately Correct (PAC) framework. More specifically we consider the following task: Given samples from some unknown dis…
View article: Reinforcement learning decoders for fault-tolerant quantum computation
Reinforcement learning decoders for fault-tolerant quantum computation Open
Topological error correcting codes, and particularly the surface code, currently provide the most feasible road-map towards large-scale fault-tolerant quantum computation. As such, obtaining fast and flexible decoding algorithms for these …
View article: Encoding-dependent generalization bounds for parametrized quantum circuits
Encoding-dependent generalization bounds for parametrized quantum circuits Open
A large body of recent work has begun to explore the potential of parametrized quantum circuits (PQCs) as machine learning models, within the framework of hybrid quantum-classical optimization. In particular, theoretical guarantees on the …
View article: Tensor network approaches for learning non-linear dynamical laws
Tensor network approaches for learning non-linear dynamical laws Open
Given observations of a physical system, identifying the underlying non-linear governing equation is a fundamental task, necessary both for gaining understanding and generating deterministic future predictions. Of most practical relevance …
View article: Stochastic gradient descent for hybrid quantum-classical optimization
Stochastic gradient descent for hybrid quantum-classical optimization Open
Within the context of hybrid quantum-classical optimization, gradient descent based optimizers typically require the evaluation of expectation values with respect to the outcome of parameterized quantum circuits. In this work, we explore t…
View article: Expressive power of tensor-network factorizations for probabilistic modeling, with applications from hidden Markov models to quantum machine learning
Expressive power of tensor-network factorizations for probabilistic modeling, with applications from hidden Markov models to quantum machine learning Open
Tensor-network techniques have enjoyed outstanding success in physics, and have recently attracted attention in machine learning, both as a tool for the formulation of new learning algorithms and for enhancing the mathematical understandin…
View article: Lieb–Robinson bounds for open quantum systems with long-ranged interactions
Lieb–Robinson bounds for open quantum systems with long-ranged interactions Open
We state and prove four types of Lieb–Robinson bounds valid for many-body open quantum systems with power law decaying interactions undergoing out of equilibrium dynamics. We also provide an introductory and self-contained discussion of th…