A high-bias, low-variance introduction to Machine Learning for physicists

  title={A high-bias, low-variance introduction to Machine Learning for physicists},
  author={P. Mehta and M. Bukov and Ching-Hao Wang and A. G. R. Day and C. Richardson and C. Fisher and D. Schwab},
  journal={Physics reports},
  • P. Mehta, M. Bukov, +4 authors D. Schwab
  • Published 2019
  • Physics, Computer Science, Mathematics, Medicine
  • Physics reports
  • Machine Learning (ML) is one of the most exciting and dynamic areas of modern research and application. The purpose of this review is to provide an introduction to the core concepts and tools of machine learning in a manner easily understood and intuitive to physicists. The review begins by covering fundamental concepts in ML and modern statistics such as the bias-variance tradeoff, overfitting, regularization, generalization, and gradient descent before moving on to more advanced topics in… CONTINUE READING
    207 Citations
    Statistical learning theory of structured data.
    • 2
    • PDF
    Machine learning and the physical sciences
    • 205
    • PDF
    Mean-field inference methods for neural networks
    • 3
    • PDF
    Learning the Ising Model with Generative Neural Networks
    • 1
    • PDF
    Active Learning Algorithm for Computational Physics
    • 4
    • PDF
    Machine Learning the Effective Hamiltonian in High Entropy Alloys
    High-dimensional inference: a statistical mechanics perspective


    Spectral Learning of Restricted Boltzmann Machines
    • 3
    • PDF
    An exact mapping between the Variational Renormalization Group and Deep Learning
    • 207
    • PDF
    Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines
    • 28
    • PDF
    Deep Learning the Ising Model Near Criticality
    • 43
    • PDF
    Machine learning phases of matter
    • 532
    • PDF