Collaborating Authors

Dunjko, Vedran

Quantum machine learning beyond kernel methods Machine Learning

With noisy intermediate-scale quantum computers showing great promise for near-term applications, a number of machine learning algorithms based on parametrized quantum circuits have been suggested as possible means to achieve learning advantages. Yet, our understanding of how these quantum machine learning models compare, both to existing classical models and to each other, remains limited. A big step in this direction has been made by relating them to so-called kernel methods from classical machine learning. By building on this connection, previous works have shown that a systematic reformulation of many quantum machine learning models as kernel models was guaranteed to improve their training performance. In this work, we first extend the applicability of this result to a more general family of parametrized quantum circuit models called data re-uploading circuits. Secondly, we show, through simple constructions and numerical simulations, that models defined and trained variationally can exhibit a critically better generalization performance than their kernel formulations, which is the true figure of merit of machine learning tasks. Our results constitute another step towards a more comprehensive theory of quantum machine learning models next to kernel formulations.

Reinforcement learning for optimization of variational quantum circuit architectures Artificial Intelligence

The study of Variational Quantum Eigensolvers (VQEs) has been in the spotlight in recent times as they may lead to real-world applications of near-term quantum devices. However, their performance depends on the structure of the used variational ansatz, which requires balancing the depth and expressivity of the corresponding circuit. In recent years, various methods for VQE structure optimization have been introduced but the capacities of machine learning to aid with this problem has not yet been fully investigated. In this work, we propose a reinforcement learning algorithm that autonomously explores the space of possible ans{\"a}tze, identifying economic circuits which still yield accurate ground energy estimates. The algorithm is intrinsically motivated, and it incrementally improves the accuracy of the result while minimizing the circuit depth. We showcase the performance of our algorithm on the problem of estimating the ground-state energy of lithium hydride (LiH). In this well-known benchmark problem, we achieve chemical accuracy, as well as state-of-the-art results in terms of circuit depth.

Variational quantum policies for reinforcement learning Artificial Intelligence

Variational quantum circuits have recently gained popularity as quantum machine learning models. While considerable effort has been invested to train them in supervised and unsupervised learning settings, relatively little attention has been given to their potential use in reinforcement learning. In this work, we leverage the understanding of quantum policy gradient algorithms in a number of ways. First, we investigate how to construct and train reinforcement learning policies based on variational quantum circuits. We propose several designs for quantum policies, provide their learning algorithms, and test their performance on classical benchmarking environments. Second, we show the existence of task environments with a provable separation in performance between quantum learning agents and any polynomial-time classical learner, conditioned on the widely-believed classical hardness of the discrete logarithm problem. We also consider more natural settings, in which we show an empirical quantum advantage of our quantum policies over standard neural-network policies. Our results constitute a first step towards establishing a practical near-term quantum advantage in a reinforcement learning setting. Additionally, we believe that some of our design choices for variational quantum policies may also be beneficial to other models based on variational quantum circuits, such as quantum classifiers and quantum regression models.

A framework for deep energy-based reinforcement learning with quantum speed-up Artificial Intelligence

In the past decade, deep learning methods have seen tremendous success in various supervised and unsupervised learning tasks such as classification and generative modeling. More recently, deep neural networks have emerged in the domain of reinforcement learning as a tool to solve decision-making problems of unprecedented complexity, e.g., navigation problems or game-playing AI. Despite the successful combinations of ideas from quantum computing with machine learning methods, there have been relatively few attempts to design quantum algorithms that would enhance deep reinforcement learning. This is partly due to the fact that quantum enhancements of deep neural networks, in general, have not been as extensively investigated as other quantum machine learning methods. In contrast, projective simulation is a reinforcement learning model inspired by the stochastic evolution of physical systems that enables a quantum speed-up in decision making. In this paper, we develop a unifying framework that connects deep learning and projective simulation, opening the route to quantum improvements in deep reinforcement learning. Our approach is based on so-called generative energy-based models to design reinforcement learning methods with a computational advantage in solving complex and large-scale decision-making problems.

On the convergence of projective-simulation-based reinforcement learning in Markov decision processes Artificial Intelligence

In recent years, the interest in leveraging quantum effects for enhancing machine learning tasks has significantly increased. Many algorithms speeding up supervised and unsupervised learning were established. The first framework in which ways to exploit quantum resources specifically for the broader context of reinforcement learning were found is projective simulation. Projective simulation presents an agent-based reinforcement learning approach designed in a manner which may support quantum walk-based speed-ups. Although classical variants of projective simulation have been benchmarked against common reinforcement learning algorithms, very few formal theoretical analyses have been provided for its performance in standard learning scenarios. In this paper, we provide a detailed formal discussion of the properties of this model. Specifically, we prove that one version of the projective simulation model, understood as a reinforcement learning approach, converges to optimal behavior in a large class of Markov decision processes. This proof shows that a physically-inspired approach to reinforcement learning can guarantee to converge.

Optimizing Quantum Error Correction Codes with Reinforcement Learning Artificial Intelligence

Quantum error correction is widely thought to be the key to fault-tolerant quantum computation. However, determining the most suited encoding for unknown error channels or specific laboratory setups is highly challenging. Here, we present a reinforcement learning framework for optimizing and fault-tolerantly adapting quantum error correction codes. We consider a reinforcement learning agent tasked with modifying a quantum memory until a desired logical error rate is reached. Using efficient simulations of a surface code quantum memory with about 70 physical qubits, we demonstrate that such a reinforcement learning agent can determine near-optimal solutions, in terms of the number of physical qubits, for various error models of interest. Moreover, we show that agents trained on one task are able to transfer their experience to similar tasks. This ability for transfer learning showcases the inherent strengths of reinforcement learning and the applicability of our approach for optimization both in off-line simulations and on-line under laboratory conditions.

Speeding-up the decision making of a learning agent using an ion trap quantum processor Artificial Intelligence

We report a proof-of-principle experimental demonstration of the quantum speed-up for learning agents utilizing a small-scale quantum information processor based on radiofrequency-driven trapped ions. The decision-making process of a quantum learning agent within the projective simulation paradigm for machine learning is implemented in a system of two qubits. The latter are realized using hyperfine states of two frequency-addressed atomic ions exposed to a static magnetic field gradient. We show that the deliberation time of this quantum learning agent is quadratically improved with respect to comparable classical learning agents. The performance of this quantum-enhanced learning agent highlights the potential of scalable quantum processors taking advantage of machine learning.

Exponential improvements for quantum-accessible reinforcement learning Artificial Intelligence

Quantum computers can offer dramatic improvements over classical devices for data analysis tasks such as prediction and classification. However, less is known about the advantages that quantum computers may bring in the setting of reinforcement learning, where learning is achieved via interaction with a task environment. Here, we consider a special case of reinforcement learning, where the task environment allows quantum access. In addition, we impose certain "naturalness" conditions on the task environment, which rule out the kinds of oracle problems that are studied in quantum query complexity (and for which quantum speedups are well-known). Within this framework of quantum-accessible reinforcement learning environments, we demonstrate that quantum agents can achieve exponential improvements in learning efficiency, surpassing previous results that showed only quadratic improvements. A key step in the proof is to construct task environments that encode well-known oracle problems, such as Simon's problem and Recursive Fourier Sampling, while satisfying the above "naturalness" conditions for reinforcement learning. Our results suggest that quantum agents may perform well in certain game-playing scenarios, where the game has recursive structure, and the agent can learn by playing against itself.

Computational speedups using small quantum devices Artificial Intelligence

Suppose we have a small quantum computer with only M qubits. Can such a device genuinely speed up certain algorithms, even when the problem size is much larger than M? Here we answer this question to the affirmative. We present a hybrid quantum-classical algorithm to solve 3SAT problems involving n>>M variables that significantly speeds up its fully classical counterpart. This question may be relevant in view of the current quest to build small quantum computers.

Optimal quantum mixing for slowly evolving sequences of Markov chains Artificial Intelligence

In this work we consider the problem of preparation of the stationary distribution of irreducible, time-reversible Markov chains, which is a fundamental task in algorithmic Markov chain theory. For the classical setting, this task has a complexity lower bound of $\Omega(\delta^{-1})$, where $\delta$ is the spectral gap of the Markov chain, and other dependencies contribute only logarithmically. In the quantum case, the conjectured complexity is $O(\sqrt{\delta^{-1}})$, with other dependencies contributing only logarithmically. However, this bound has only been achieved for a few special classes of Markov chains. In this work, we provide a method for the sequential preparation of stationary distributions for sequences of time-reversible $N$-state Markov chains, akin to the setting of simulated annealing methods. The complexity of preparation we achieve is $O(\sqrt{\delta^{-1}} \sqrt[4]{N})$, neglecting logarithmic factors. While this result falls short of the conjectured optimal time, it provides a quadratic improvement over na\"{i}ve approaches. Moreover, for the case when the output distributions are required to be encoded in pure quantum states we identify the settings where our algorithm is strictly optimal. The settings of slowly evolving sequences of Markov chains naturally appear in reinforcement learning, and consequently our results can be readily applied in quantum machine learning as well.