Search Results for author:
Found 6 papers, 3 papers with code
Bayesian RG Flow in Neural Network Field Theories
In this paper, we unify NNFT and BRG to form a powerful new framework for exploring the space of NNs and SFTs, which we coin BRG-NNFT.
Asymptotic theory of in-context learning by linear attention
Transformers have a remarkable ability to learn and execute tasks based on examples provided within the input itself, without explicit prior training.
Wilsonian Renormalization of Neural Network Gaussian Processes
We systematically integrate out the unlearnable modes of the GP kernel, thereby obtaining an RG flow of the Gaussian Process in which the data plays the role of the energy scale.
Neural Network Field Theories: Non-Gaussianity, Actions, and Locality
Conversely, the correspondence allows one to engineer architectures realizing a given field theory by representing action deformations as deformations of neural network parameter densities.
Symmetry-via-Duality: Invariant Neural Network Densities from Parameter-Space Correlators
We demonstrate that symmetries of network densities may be determined via dual computations of network correlation functions, even when the density is unknown and the network is not equivariant.
Neural Networks and Quantum Field Theory
We propose a theoretical understanding of neural networks in terms of Wilsonian effective field theory.
