Exact analytical expression for the time-dependent maximum Lyapunov exponent during transients in a network supporting dynamics-based computation.
arXiv preprint arXiv:2410.13821 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 6roles
background 1polarities
background 1representative citing papers
Introduces an information-theoretic formalization of the binding problem and a probing method to quantify binding information in deep learning model representations, tested on ViTs across challenging datasets.
Equivariant neural networks support Goldstone-like modes enabling coherent information propagation across depth and recurrent iterations.
Manifold constraints via the new MACRO optimizer independently bound activation scales and enforce rotational equilibrium in LLM pre-training, subsuming RMS normalization and decoupled weight decay while delivering competitive performance with convergence guarantees.
S4D state space models correspond exactly to wave propagation and nonlinear wave interactions in a one-dimensional ring oscillator network, with a closed-form operator describing the complete input-output map.
citing papers explorer
-
Exact expression for maximum Lyapunov exponent during transients in computationally powerful dynamical networks
Exact analytical expression for the time-dependent maximum Lyapunov exponent during transients in a network supporting dynamics-based computation.
-
Formalizing the Binding Problem
Introduces an information-theoretic formalization of the binding problem and a probing method to quantify binding information in deep learning model representations, tested on ViTs across challenging datasets.
-
Spontaneous symmetry breaking and Goldstone modes for deep information propagation
Equivariant neural networks support Goldstone-like modes enabling coherent information propagation across depth and recurrent iterations.
-
Demystifying Manifold Constraints in LLM Pre-training
Manifold constraints via the new MACRO optimizer independently bound activation scales and enforce rotational equilibrium in LLM pre-training, subsuming RMS normalization and decoupled weight decay while delivering competitive performance with convergence guarantees.
-
An explicit operator explains end-to-end computation in the modern neural networks used for sequence and language modeling
S4D state space models correspond exactly to wave propagation and nonlinear wave interactions in a one-dimensional ring oscillator network, with a closed-form operator describing the complete input-output map.
- Understanding LoRA as Knowledge Memory: An Empirical Analysis