Search Results for author: Vedran Dunjko

Found 23 papers, 5 papers with code

Parametrized Quantum Policies for Reinforcement Learning

no code implementations NeurIPS 2021 Sofiene Jerbi, Casper Gyurik, Simon Marshall, Hans Briegel, Vedran Dunjko

With the advent of real-world quantum computing, the idea that parametrized quantum computations can be used as hypothesis families in a quantum-classical machine learning system is gaining increasing traction.

Quantum machine learning beyond kernel methods

1 code implementation25 Oct 2021 Sofiene Jerbi, Lukas J. Fiderer, Hendrik Poulsen Nautrup, Jonas M. Kübler, Hans J. Briegel, Vedran Dunjko

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.

Quantum Machine Learning

Structural risk minimization for quantum linear classifiers

no code implementations12 May 2021 Casper Gyurik, Dyon van Vreumingen, Vedran Dunjko

In this paper we investigate capacity measures of two closely related QML models called explicit and implicit quantum linear classifiers (also called the quantum variational method and quantum kernel estimator) with the objective of identifying new ways to implement structural risk minimization -- i. e., how to balance between training accuracy and generalization performance.

Quantum Machine Learning

Reinforcement learning for optimization of variational quantum circuit architectures

no code implementations NeurIPS 2021 Mateusz Ostaszewski, Lea M. Trenkwalder, Wojciech Masarczyk, Eleanor Scerri, Vedran Dunjko

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.

Variational quantum policies for reinforcement learning

no code implementations9 Mar 2021 Sofiene Jerbi, Casper Gyurik, Simon Marshall, Hans J. Briegel, Vedran Dunjko

First, we investigate how to construct and train reinforcement learning policies based on variational quantum circuits.

Quantum Machine Learning

Certificates of quantum many-body properties assisted by machine learning

1 code implementation5 Mar 2021 Borja Requena, Gorka Muñoz-Gil, Maciej Lewenstein, Vedran Dunjko, Jordi Tura

A number of standard methods are used to tackle such problems: variational approaches focus on parameterizing a subclass of solutions within the feasible set; in contrast, relaxation techniques have been proposed to approximate it from outside, thus complementing the variational approach by providing ultimate bounds to the global optimal solution.

Transfer Learning Quantum Physics

Towards quantum advantage via topological data analysis

no code implementations6 May 2020 Casper Gyurik, Chris Cade, Vedran Dunjko

Our results provide a number of useful applications for full-blown, and restricted quantum computers with a guaranteed exponential speedup over classical methods, recovering some of the potential for linear-algebraic QML to become one of quantum computing's killer applications.

Quantum Machine Learning Topological Data Analysis

Quantum enhancements for deep reinforcement learning in large spaces

1 code implementation28 Oct 2019 Sofiene Jerbi, Lea M. Trenkwalder, Hendrik Poulsen Nautrup, Hans J. Briegel, Vedran Dunjko

In the past decade, the field of quantum machine learning has drawn significant attention due to the prospect of bringing genuine computational advantages to now widespread algorithmic methods.

Decision Making Quantum Machine Learning

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

no code implementations25 Oct 2019 Walter L. Boyajian, Jens Clausen, Lea M. Trenkwalder, Vedran Dunjko, Hans J. Briegel

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.

Optimizing Quantum Error Correction Codes with Reinforcement Learning

no code implementations20 Dec 2018 Hendrik Poulsen Nautrup, Nicolas Delfosse, Vedran Dunjko, Hans J. Briegel, Nicolai Friis

Using efficient simulations with about 70 data qubits with arbitrary connectivity, we demonstrate that such a reinforcement learning agent can determine near-optimal solutions, in terms of the number of data qubits, for various error models of interest.

Transfer Learning

Computational speedups using small quantum devices

no code implementations24 Jul 2018 Vedran Dunjko, Yimin Ge, J. Ignacio Cirac

Suppose we have a small quantum computer with only M qubits.

Smooth input preparation for quantum and quantum-inspired machine learning

no code implementations1 Apr 2018 Zhikuan Zhao, Jack K. Fitzsimons, Patrick Rebentrost, Vedran Dunjko, Joseph F. Fitzsimons

Machine learning has recently emerged as a fruitful area for finding potential quantum computational advantage.

Neural Network Operations and Susuki-Trotter evolution of Neural Network States

1 code implementation6 Mar 2018 Nahuel Freitas, Giovanna Morigi, Vedran Dunjko

We show that this parametrization contains a set of universal quantum gates, from which it follows that the state prepared by any quantum circuit can be expressed as a Neural Network State with a number of hidden nodes that grows linearly with the number of elementary operations in the circuit.

Quantum Physics

Exponential improvements for quantum-accessible reinforcement learning

no code implementations30 Oct 2017 Vedran Dunjko, Yi-Kai Liu, Xingyao Wu, Jacob M. Taylor

Quantum computers can offer dramatic improvements over classical devices for data analysis tasks such as prediction and classification.

Machine learning \& artificial intelligence in the quantum domain

no code implementations8 Sep 2017 Vedran Dunjko, Hans J. Briegel

For instance, quantum computing is finding a vital application in providing speed-ups in ML, critical in our "big data" world.

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

no code implementations5 Sep 2017 Theeraphot Sriarunothai, Sabine Wölk, Gouri Shankar Giri, Nicolai Friis, Vedran Dunjko, Hans J. Briegel, Christof Wunderlich

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.

Decision Making

Active learning machine learns to create new quantum experiments

no code implementations2 Jun 2017 Alexey A. Melnikov, Hendrik Poulsen Nautrup, Mario Krenn, Vedran Dunjko, Markus Tiersch, Anton Zeilinger, Hans J. Briegel

We investigate this question by using the projective simulation model, a physics-oriented approach to artificial intelligence.

Active Learning

Quantum-enhanced machine learning

no code implementations26 Oct 2016 Vedran Dunjko, Jacob M. Taylor, Hans J. Briegel

Within our approach, we tackle the problem of quantum enhancements in reinforcement learning as well, and propose a systematic scheme for providing improvements.

Quantum Machine Learning

Meta-learning within Projective Simulation

no code implementations25 Feb 2016 Adi Makmal, Alexey A. Melnikov, Vedran Dunjko, Hans J. Briegel

The extended model is examined on three different kinds of reinforcement learning tasks, in which the agent has different optimal values of the meta-parameters, and is shown to perform well, reaching near-optimal to optimal success rates in all of them, without ever needing to manually adjust any meta-parameter.

Meta-Learning

Framework for learning agents in quantum environments

no code implementations30 Jul 2015 Vedran Dunjko, Jacob M. Taylor, Hans J. Briegel

In this paper we provide a broad framework for describing learning agents in general quantum environments.

Projective simulation with generalization

no code implementations9 Apr 2015 Alexey A. Melnikov, Adi Makmal, Vedran Dunjko, Hans J. Briegel

Specifically, we show that already in basic (but extreme) environments, learning without generalization may be impossible, and demonstrate how the presented generalization machinery enables the projective simulation agent to learn.

Faster quantum mixing for slowly evolving sequences of Markov chains

no code implementations4 Mar 2015 Davide Orsucci, Hans J. Briegel, Vedran Dunjko

Markov chain methods are remarkably successful in computational physics, machine learning, and combinatorial optimization.

Combinatorial Optimization

Cannot find the paper you are looking for? You can Submit a new open access paper.