Many body seminar: How to increase the interpretability and reliability of any ML model?

Anna Dawid-Łękowska (ICFO and University of Warsaw):
Identifying phase transitions is one of the key problems in quantum
many-body physics.

October 28, 2021

Anna Dawid-Łękowska (ICFO and University of Warsaw)
Group seminar via Zoom (hybrid format: online/seminar room B2.46)
Thu, 29. October 2021, 11:20 am (MEZ)

Abstract:


Identifying phase transitions is one of the key problems in quantum
many-body physics. The challenge is the exponential growth of the
complexity of quantum systems’ description with the number of studied
particles, which quickly renders exact numerical analysis impossible.
A promising alternative is to harness the power of machine learning
(ML) methods designed to deal with large datasets [1]. However, ML
models, and especially neural networks (NNs), are known for their
black-box construction, i.e., they usually hinder any insight into the
reasoning behind their predictions. As a result, if we apply ML to
novel problems, neither we can fully trust their predictions (lack of
reliability) nor learn what the ML model learned (lack of
interpretability). I will present a set of Hessian-based methods
opening the black box of ML models, increasing their interpretability
and reliability. We demonstrate how these methods can guide physicists
in understanding patterns responsible for the phase transition. We
also show that influence functions allow checking that the NN, trained
to recognize known quantum phases, can predict new unknown ones. We
present this power both for the numerically simulated data from the
one-dimensional extended spinless Fermi-Hubbard model [2] and
experimental topological data [3]. We also show how we can generate
error bars for the NN’s predictions and check whether the NN predicts
using extrapolation instead of extracting information from the
training data [4]. The presented toolbox is entirely independent of
the ML model’s architecture and is thus applicable to various physical
problems.
[1] J. Carrasquilla. (2020). Machine learning for quantum matter,
Advances in Physics: X, 5:1.
[2] A. Dawid et al. (2020). Phase detection with neural networks:
interpreting the black box. New J. Phys. 22, 115001.
[3] N. Käming, A. Dawid, K. Kottmann et al. (2021). Unsupervised
machine learning of topological phase transitions from experimental
data. Mach. Learn.: Sci. Technol. 2, 035037.
[4] A. Dawid et al. (2021). Hessian-based toolbox for interpretable
and reliable machine learning in physics. arXiv:2108.02154.

 

Go to Editor View