Cover Image

Sliding down the stairs: how correlated latent variables accelerate learning with neural networks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bardone, Lorenzo, Goldt, Sebastian
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Statistical Mechanics Probability Statistics Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions
by: Ricci, Fabiola, et al.
Published: (2025)

Learning from higher-order statistics, efficiently: hypothesis tests, random features, and neural networks
by: Székely, Eszter, et al.
Published: (2023)

A Fourier perspective on the learning dynamics of neural networks: from sample complexities to mechanistic insights
by: Ricci, Fabiola, et al.
Published: (2026)

Pointwise Generalization in Deep Neural Networks
by: Li, Shaojie, et al.
Published: (2026)

Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation
by: Giorlandino, Alessio, et al.
Published: (2025)

The impact of memory on learning sequence-to-sequence tasks
by: Seif, Alireza, et al.
Published: (2022)

Model-free learning of probability flows: Elucidating the nonequilibrium dynamics of flocking
by: Boffi, Nicholas M., et al.
Published: (2024)

Expansion of net correlations in terms of partial correlations
by: Arenaza, Bautista, et al.
Published: (2024)

Data efficiency, dimensionality reduction, and the generalized symmetric information bottleneck
by: Martini, K. Michael, et al.
Published: (2023)

Deep Variational Multivariate Information Bottleneck -- A Framework for Variational Losses
by: Abdelaleem, Eslam, et al.
Published: (2023)

Gaussian mixtures and non-parametric likelihoods through the lens of statistical mechanics
by: Ghosh, Subhroshekhar, et al.
Published: (2026)

Additive-Functional Approach to Transport in Periodic and Tilted Periodic Potentials
by: Yang, Sang, et al.
Published: (2026)

Unsupervised learning of anomalous diffusion data
by: Muñoz-Gil, Gorka, et al.
Published: (2021)

Dropout Neural Network Training Viewed from a Percolation Perspective
by: Devlin, Finley, et al.
Published: (2025)

Nonlinear spiked covariance matrices and signal propagation in deep neural networks
by: Wang, Zhichao, et al.
Published: (2024)

Statistical limits of correlation detection in trees
by: Ganassali, Luca, et al.
Published: (2022)

Bayesian symbolic regression: Automated equation discovery from a physicists' perspective
by: Guimera, Roger, et al.
Published: (2025)

Hierarchical geometric deep learning enables scalable analysis of molecular dynamics
by: Pengmei, Zihan, et al.
Published: (2025)

Memorisation, convergence and generalisation in generative models
by: Maillard, Antoine, et al.
Published: (2026)

Compression, Regularity, Randomness and Emergent Structure: Rethinking Physical Complexity in the Data-Driven Era
by: Dehghani, Nima
Published: (2025)

Gaussian random field approximation via Stein's method with applications to wide random neural networks
by: Balasubramanian, Krishnakumar, et al.
Published: (2023)

Deep learning of phase transitions with minimal examples
by: Abuali, Ahmed, et al.
Published: (2025)

Iterative variational learning of committor-consistent transition pathways using artificial neural networks
by: Megías, Alberto, et al.
Published: (2024)

Weak Correlations as the Underlying Principle for Linearization of Gradient-Based Learning Systems
by: Shem-Ur, Ori, et al.
Published: (2024)

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

Physical networks as network-of-networks
by: Pete, Gábor, et al.
Published: (2023)

Limit theorems of Chatterjee's rank correlation
by: Lin, Zhexiao, et al.
Published: (2022)

Factual recall in linear associative memories: sharp asymptotics and mechanistic insights
by: Giorlandino, Alessio, et al.
Published: (2026)

Colored Stochastic Multiplicative Processes with Additive Noise Unveil a Third-Order PDE, Defying Conventional FPE and Fick-Law Paradigms
by: Bianucci, Marco, et al.
Published: (2024)

Mean First Passage Time of the Symmetric Noisy Voter Model with Arbitrary Initial and Boundary Conditions
by: Kazakevičius, Rytis, et al.
Published: (2025)

Review and Prospect of Algebraic Research in Equivalent Framework between Statistical Mechanics and Machine Learning Theory
by: Watanabe, Sumio
Published: (2024)

Susceptibilities and Patterning: A Primer on Linear Response in Bayesian Learning
by: Elliott, Chris, et al.
Published: (2026)

Statistics of Min-max Normalized Eigenvalues in Random Matrices
by: Nakada, Hyakka, et al.
Published: (2025)

Laws of thermodynamics for exponential families
by: Balsubramani, Akshay
Published: (2025)

Entropy of spatial network with applications to non-extensive statistical mechanics
by: Kazemi, O. K., et al.
Published: (2025)

Local-global correlations of dynamics on disordered energy landscapes
by: Calvert, Jacob, et al.
Published: (2025)

Are Bayesian networks typically faithful?
by: Boeken, Philip, et al.
Published: (2024)

An exact multiple-time-step variational formulation for the committor and the transition rate
by: Lorpaiboon, Chatipat, et al.
Published: (2025)

Thermodynamic bounds on energy use in quasi-static Deep Neural Networks
by: Tkachenko, Alexei V.
Published: (2025)

Inference in conditioned dynamics through causality restoration
by: Braunstein, Alfredo, et al.
Published: (2022)