mlsanityData to 14 Oct 2026

Renormalization in the neural network-quantum field theory correspondence

arXiv 2212.11811 ↗First posted 22 Dec 2022hep-th cond-mat.dis-nn cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

A statistical ensemble of neural networks can be described in terms of a quantum field theory (NN-QFT correspondence). The infinite-width limit is mapped to a free field theory, while finite N corrections are mapped to interactions. After reviewing the correspondence, we will describe how to implement renormalization in this context and discuss preliminary numerical results for translation-invariant kernels. A major outcome is that changing the standard deviation of the neural network weight distribution corresponds to a renormalization flow in the space of networks.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 25 of its 48 references that are in the map. First posted on arXiv 22 Dec 2022.

Builds on

25 of 48 references.

References · 25

  1. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,254
  2. 2017Visualizing the Loss Landscape of Neural Netscited by 1,130
  3. 2016Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimizationcited by 699
  4. 2019Quantifying the Carbon Emissions of Machine Learningcited by 521
  5. 2018BOHB: Robust and Efficient Hyperparameter Optimization at Scalecited by 470
  6. 2020Discovering Symbolic Models from Deep Learning with Inductive Biasescited by 344
  7. 2017The Expressive Power of Neural Networks: A View from the Widthcited by 320
  8. 2016On the Expressive Power of Deep Neural Networkscited by 306
  9. 2020A Survey on Neural Network Interpretabilitycited by 291
  10. 2014The Loss Surfaces of Multilayer Networkscited by 280
  11. 2020Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learningcited by 249
  12. 2019Explainable Machine Learning for Scientific Insights and Discoveriescited by 166
13 more
  1. 2019Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processescited by 151
  2. 2016Why does deep and cheap learning work so well?cited by 100
  3. 2020The Cost of Training NLP Models: A Concise Overviewcited by 98
  4. 2020Neural Networks and Quantum Field Theorycited by 61
  5. 2014An exact mapping between the Variational Renormalization Group and Deep Learningcited by 56
  6. 2018The Challenge of Crafting Intelligible Intelligencecited by 47
  7. 2020A Survey of Deep Learning for Scientific Discoverycited by 36
  8. 2021Symmetry-via-Duality: Invariant Neural Network Densities from Parameter-Space Correlatorscited by 29
  9. 2021Building Quantum Field Theories Out of Neuronscited by 28
  10. 2021Nonperturbative renormalization for the neural network-QFT correspondencecited by 24
  11. 2021The edge of chaos: quantum field theory and deep neural networkscited by 24
  12. 2017A Correspondence Between Random Neural Networks and Statistical Field Theorycited by 14
  13. 2018Inferring relevant features: from QFT to PCAcited by 2

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 4; 2025: 1.

7 papers.

  1. 2023Structures of Neural Network Effective Theoriescited by 13
  2. 2024Bayesian RG Flow in Neural Network Field Theoriescited by 9
  3. 2024NCoder -- A Quantum Field Theory approach to encoding datacited by 8
  4. 2024Wilsonian Renormalization of Neural Network Gaussian Processescited by 8
  5. 2025The neural networks with tensor weights and emergent fermionic Wick rules in the large-width limitcited by 2
  6. 2023Black holes and the loss landscape in machine learningcited by 0
  7. 2024A Scale-Invariant Diagnostic Approach Towards Understanding Dynamics of Deep Neural Networkscited by 0