This is the webpage for the seminar I ran on statistical mechanics in metauni. The purpose of this seminar was to learn about statistical mechanics, with a view towards understanding apparent ‘phase transitions’ in deep learning.

Speakers

Talks

  • 3/8/23 (Rohan) What is statistical mechanics? Hamiltonian systems and Liouville’s theorem. (notes, video)
  • 17/8/23 (Rohan) Entropy and the Boltzmann distribution. (notes, video)
  • 31/8/23 (Rohan) Stochastic processes. (notes, video)
  • 14/9/23 (Rohan) Stochastic differential equations. (notes)
  • 28/9/23 (Rohan) Discussing the paper “Statistical Mechanics of Learning from Examples” (1992) by H. S. Seung, H. Sompolinsky and N. Tishby. (notes)
  • 30/11/23 (Ben) Statistical Field Theory 1: 1D Ising Model to Spin-1/2 Part 1. (notes)
  • 14/12/23 (Ben) Statistical Field Theory 1: Introduction and 1D Ising Model to Spin-1/2 Part 2. (notes)
  • 18/12/23 (Ben) Statistical Field Theory 2: 2D Classical Ising Model to 1D Quantum Ising Model Part 1. (notes)

Texts

  • Pathria and Beale (2011) Statistical Mechanics
  • E. T. Jaynes (1957) “Information Theory and Statistical Mechanics” Physical Review 106.4 pp. 620-630
  • B. Øksendal (2013) Stochastic differential equations
  • J. H. Manton (2013) “A Primer on Stochastic Differential Geometry for Signal Processing” IEEE Journal of Selected Topics in Signal Processing, 7.4 pp. 681–699 http://arxiv.org/abs/1302.0430
  • H. S. Seung, H. Sompolinsky and N. Tishby (1992) “Statistical Mechanics of Learning from Examples” Physical Review A 45.8 pp. 6056-6091