Statistical Field Theory

By Giorgio Parisi, R. Shankar. 1988

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. David M. Blei
2. Yoshua Bengio
3. Matthew D. Hoffman
4. Chong Wang
5. Ruslan Salakhutdinov
6. Rajesh Ranganath
7. Sergey Levine
8. Zhe Gan

Citations in the corpus

• Variational Inference: A Review for Statisticians (2016, methodology): “el, yet separate, tracks. Peterson and Anderson (1987) is arguably the first variational procedure for a particular model: a neural network. This paper, along with insights from statistical mechanics (Parisi, 1988), led to a flurry of variational inference procedures for a wide class of models (Saul e”
• Mean Field Theory for Sigmoid Belief Networks (1996, methodology): “Our approach in this paper relies on a di erent tool from statistical mechanics|namely, mean eld theory (Parisi, 1988).”
• Geometry of quantum phase transitions (2019, background): “In the past few decades, the studies of phase transitions at zero and finite temperature has been fuelled by the formidable success of Ginzburg-Landau-Wilson theories, local ordering, spontaneous symmetry breaking and the renormalisation group [13, 14, 15, 16] in spelling out the nature of a wide va”
• Spin-glass theory for pedestrians (2005, background): “Pure states In the low temperature phase, and in the limit N → ∞ we can have ergodicity breaking: the system at equilibrium explores only a sub-part of the phase space [6, 7, 4].”
• Stochastic variational inference (2012, background): “(1996); Saul and Jordan (1996) and Jaakkola (1997) grew out of reading the statistical physics literature (Peterson and Anderson, 1987; Parisi, 1988). In parallel, the mean-field methods explained in Neal and Hinton (1999) (originally published in 1993) and Hinton and Van Camp (1993) led to variatio”