6 papers
Bulk-boundary decomposition of neural networks
Donghee Lee, Hye-Sung Lee, Jaeok Yi
We present the bulk--boundary decomposition as a new framework for understanding the training dynamics of deep neural networks. Starting from the stochastic gradient descent formul…
GlueNN: gluing patchwise analytic solutions with neural networks
Doyoung Kim, Donghee Lee, Hye-Sung Lee +2
In the analysis of complex physical systems, the objective often extends beyond merely computing a numerical solution to capturing the precise crossover between different regimes a…
BCS superconductivity in the presence of wave dark matter
Yechan Kim, Hye-Sung Lee, Jiheon Lee +1
In the established era of dark matter, condensed matter Hamiltonians-including those of superconductors-may require extension to account for the surrounding Galactic environment. W…
Dark energy under a gauge symmetry: A review of gauged quintessence and its implications
Kunio Kaneta, Hye-Sung Lee, Jiheon Lee +1
We review the gauged quintessence scenario, wherein the quintessence scalar field responsible for dark energy is promoted to a complex field charged under a dark gauge symme…
Synaptic Field Theory for Neural Networks
Donghee Lee, Hye-Sung Lee, Jaeok Yi
Theoretical understanding of deep learning remains elusive despite its empirical success. In this study, we propose a novel "synaptic field theory" that describes the training dyna…
Dynamic neuron approach to deep neural networks: Decoupling neurons for renormalization group analysis
Donghee Lee, Hye-Sung Lee, Jaeok Yi
Deep neural network architectures often consist of repetitive structural elements. We introduce an approach that reveals these patterns and can be broadly applied to the study of d…