Cover Image

Opening the Black Box: predicting the trainability of deep neural networks with reconstruction entropy

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Thurn, Yanick, Jefferson, Ro, Erdmenger, Johanna
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Disordered Systems and Neural Networks High Energy Physics - Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Wilsonian Renormalization of Neural Network Gaussian Processes
by: Howard, Jessica N., et al.
Published: (2024)

Gauge-covariant stochastic neural fields: Stability and finite-width effects
by: Terin, Rodrigo Carmo
Published: (2025)

The neural networks with tensor weights and emergent fermionic Wick rules in the large-width limit
by: Huang, Guojun, et al.
Published: (2025)

Learning topological defects formation with neural networks in a quantum phase transition
by: Shi, Han-Qing, et al.
Published: (2022)

Bulk-boundary decomposition of neural networks
by: Lee, Donghee, et al.
Published: (2025)

Towards Worst-Case Guarantees with Scale-Aware Interpretability
by: Greenspan, Lauren, et al.
Published: (2026)

Phase diagram and eigenvalue dynamics of stochastic gradient descent in multilayer neural networks
by: Park, Chanju, et al.
Published: (2025)

Emergent weight morphologies in deep neural networks
by: de Jong, Pascal, et al.
Published: (2025)

Krylov space approach to Singular Value Decomposition in non-Hermitian systems
by: Nandy, Pratik, et al.
Published: (2024)

Computing frustration and near-monotonicity in deep neural networks
by: Wendin, Joel, et al.
Published: (2025)

Finite-time Lyapunov exponents of deep neural networks
by: Storm, L., et al.
Published: (2023)

Topological Effects in Neural Network Field Theory
by: Ferko, Christian, et al.
Published: (2026)

Lecture Notes on Statistical Physics and Neural Networks
by: Hohm, Olaf
Published: (2026)

Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks
by: He, Tianyu, et al.
Published: (2024)

A Two-Phase Perspective on Deep Learning Dynamics
by: Koch, Robert de Mello, et al.
Published: (2025)

Neural Network Quantum Field Theory from Transformer Architectures
by: Ageev, Dmitry S., et al.
Published: (2026)

Bayesian RG Flow in Neural Network Field Theories
by: Howard, Jessica N., et al.
Published: (2024)

Detecting quantum chaos via pseudo-entropy
by: He, Song, et al.
Published: (2024)

Gauge covariant neural network for quarks and gluons
by: Nagai, Yuki, et al.
Published: (2021)

Implicit bias produces neural scaling laws in learning curves, from perceptrons to deep networks
by: D'Amico, Francesco, et al.
Published: (2025)

The Underlying Scaling Laws and Universal Statistical Structure of Complex Datasets
by: Levi, Noam, et al.
Published: (2023)

Grokking Modular Polynomials
by: Doshi, Darshil, et al.
Published: (2024)

Random matrix theory of sparse neuronal networks with heterogeneous timescales
by: Chotibut, Thiparat, et al.
Published: (2025)

The twin peaks of learning neural networks
by: Demyanenko, Elizaveta, et al.
Published: (2024)

Neural Scaling Laws From Large-N Field Theory: Solvable Model Beyond the Ridgeless Limit
by: Zhang, Zhengkang
Published: (2024)

High-dimensional learning of narrow neural networks
by: Cui, Hugo
Published: (2024)

Neural network representation of quantum systems
by: Hashimoto, Koji, et al.
Published: (2024)

Spring-block theory of feature learning in deep neural networks
by: Shi, Cheng, et al.
Published: (2024)

Holographic reconstruction of black hole spacetime: machine learning and entanglement entropy
by: Ahn, Byoungjoon, et al.
Published: (2024)

Robust Reasoning as a Symmetry-Protected Topological Phase
by: Sung, Ilmo
Published: (2026)

Information-theoretic reduction of deep neural networks to linear models in the overparametrized proportional regime
by: Camilli, Francesco, et al.
Published: (2025)

Supervised and Unsupervised protocols for hetero-associative neural networks
by: Alessandrelli, Andrea, et al.
Published: (2025)

Deep neural networks from the perspective of ergodic theory
by: Zhang, Fan
Published: (2023)

Fixed width treelike neural networks capacity analysis -- generic activations
by: Stojnic, Mihailo
Published: (2024)

High-dimensional manifold of solutions in neural networks: insights from statistical physics
by: Malatesta, Enrico M.
Published: (2023)

Training neural networks with structured noise improves classification and generalization
by: Benedetti, Marco, et al.
Published: (2023)

Exact capacity of the \emph{wide} hidden layer treelike neural networks with generic activations
by: Stojnic, Mihailo
Published: (2024)

Bayes-optimal learning of an extensive-width neural network from quadratically many samples
by: Maillard, Antoine, et al.
Published: (2024)

How does training shape the Riemannian geometry of neural network representations?
by: Zavatone-Veth, Jacob A., et al.
Published: (2023)

Towards a theory of how the structure of language is acquired by deep neural networks
by: Cagnetta, Francesco, et al.
Published: (2024)