Ellis Fellows program Quantum and Physics based machine learning (QPhML)
Increased computational power and data availability, as
well as algorithmic advances, have led to impressive machine learning
applications in many areas such as computer vision, pattern recognition,
robotics and AI. At the same time, conventional CMOS technology is reaching its physical
limits and the energy consumption of computing is reaching alarming proportions.
There is therefore a great need to design novel computing paradigms that face these challenges.
The aim of the Ellis program Quantum and Physics based machine learning (QPhML) is to use concepts from quantum physics and statistical physics to develop novel machine
learning algorithms with the ultimate aim to realize novel future, possibly energy efficient, hardware implementations.
The program is part of the recent European initiative called Ellis (European Laboratory for Learning and Intelligent Systems) ELLIS to stimulate research on machine learning by building networks of top reseach groups in Europe.
The program focuses on the following directions:
Quantum enhanced machine learning.
Quantum devices are nearing the noisy intermediate scale quantum (NISQ)
era, corresponding to machines with 50 to 100 qubits and capable of
executing circuits with depths on the order of thousands of elementary
two qubit operations. NISQ devices may provide computational
advantages over classical supercomputers for various machine learning problems, which
includes sampling from hard-to-simulate probability distributions for Bayesian methods and the Quantum Boltzmann Machine and linear algebra problems (for instance for kernel methods or deep learning).
It is hoped that the application of NISQ technology to machine learning may be
one of the first instances exhibiting genuine quantum
Statistical physics approach to machine learning
Noise plays a fundamental role for learning in large neural networks. Rather than designing reliable bits and use software to generate random numbers, an appealing
alternative is to design hardware that is noisy by design. Such devices would be much more energy efficient.
Methods from non-equilibrium statistical physics are well suited to improve our understanding of stochastic systems.
An example is the use of physically coupled replicas that have been shown to be very effective for hard combinatoric or strongly non-linear learning problems.
In addition, the observation that physical replicas resemble Trotterized quantum systems provides a promising new research direction for the design of
stochastic or quantum learning algorithms. Another link between quantum and
stochastic systems is the observation that sign free quantum systems can
be mapped onto classical stochastic diffusion problems.
Using machine learning for quantum physics
The challenge of quantum
many-body physics is to efficiently describe and control exponential
numbers of parameters of quantum systems. Better characterization of
such systems will lead to the understanding of quantum materials such
as high-temperature superconductors or topological insulators. Enhanced
control of immense parameter spaces will improve the understanding and
design of quantum devices, enabling quantum computers and networks. For
this problem, machine learning offers a new option.
The Ellis program is realized through the active involvement of the Ellis Fellows (senior researchers) and Ellis Scholars (more junior researchers).
In addition, the Ellis Guests, are affiliated researchers.
Bert Kappen. Department of Biophysics, Radboud University Nijmegen, firstname.lastname@example.org (program director)
Riccardo Zecchina Department of Decision Sciences Bocconi University Milan, email@example.com (program director)
Miguel Angel Delgado. Department of Theoretical physics Universidad Complutense Madrid, firstname.lastname@example.org
David Gross. Institute for Theoretical physics University Cologne. email@example.com
Florian Marquardt. Institute for Theoretical physics, Max Planck Institute Erlangen. firstname.lastname@example.org
Matthias Rupp. Department of Theory. Fritz-Haber-Institut of the Max Planck Society. email@example.com
Gabor Csanyi. Department of Engineering, University of Cambridge. firstname.lastname@example.org
Florent Krzakala, Department of Physics, Ecole Normal Superieur Paris. email@example.com
Guilio Biroli. Department of Physics, Ecole Normal Superieur Paris. firstname.lastname@example.org
Lenka Zdeborova. Institute for theoretical physics, University Paris-Saclay. email@example.com
Jens Eisert. Dahlem Center for Complex Quantum Systems Free University Berlin. firstname.lastname@example.org
Giuseppe Santoro. SISSA Trieste. email@example.com
Remi Monasson Department of Physics, Ecole Normal Superieur Paris. firstname.lastname@example.org
Carlo Baldassi. Department of Decision Sciences Bocconi University Milan. email@example.com
Vedran Dunjko. Leiden Institute for Advanced Computer Science University Leiden. firstname.lastname@example.org
Giuseppe Carleo. Center for Computational Quantum Physics, Flatiron Institute, New York, email@example.com
Marc Mezard. Department of Physics, Ecole Normal Superieur Paris
Nicolas Regnault. Department of Physics, Ecole Normal Superieur Paris
Jorge Kurchan. Department of Physics, Ecole Normal Superieur Paris
Matthias Troyer. ETH Zurich and Microsoft Research
Manfred Opper. TU Berlin
Aram Harrow. MIT, USA
Valentina Ros. Department of Physics, Ecole Normal Superieur Paris
Andrea Rocchetto. Department of Computer Science, University of Texas at Austin, USA
Ellis QPhML workshop. The DALI conference. San Sebastian, 5 September 2019