Copertina

Mapping of attention mechanisms to a generalized Potts model

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Rende, Riccardo, Gerace, Federica, Laio, Alessandro, Goldt, Sebastian
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Disordered Systems and Neural Networks Statistical Mechanics Computation and Language Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

Statistical mechanics of transfer learning in fully-connected networks in the proportional limit
di: Ingrosso, Alessandro, et al.
Pubblicazione: (2024)

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

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

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

How transformers learn structured data: insights from hierarchical filtering
di: Garnier-Brun, Jerome, et al.
Pubblicazione: (2024)

The Physics of Data and Tasks: Theories of Locality and Compositionality in Deep Learning
di: Favero, Alessandro
Pubblicazione: (2025)

Generalization Dynamics of Linear Diffusion Models
di: Merger, Claudia, et al.
Pubblicazione: (2025)

Distinct mechanisms underlying in-context learning in transformers
di: Gibson, Cole, et al.
Pubblicazione: (2026)

The phase boundary of the random site Ising model
di: Zinati, Riccardo Ben Alì, et al.
Pubblicazione: (2026)

Ordering transition of the three-dimensional four-state random-field Potts model
di: Kumar, Manoj, et al.
Pubblicazione: (2025)

Pseudo-likelihood produces associative memories able to generalize, even for asymmetric couplings
di: D'Amico, Francesco, et al.
Pubblicazione: (2025)

Semi-analytic approximate stability selection for correlated data in generalized linear models
di: Takahashi, Takashi, et al.
Pubblicazione: (2020)

Nonequilbrium physics of generative diffusion models
di: Yu, Zhendong, et al.
Pubblicazione: (2024)

A theoretical framework for overfitting in energy-based modeling
di: Catania, Giovanni, et al.
Pubblicazione: (2025)

Cascade of phase transitions in the training of Energy-based models
di: Bachtis, Dimitrios, et al.
Pubblicazione: (2024)

Discrete generative diffusion models without stochastic differential equations: a tensor network approach
di: Causer, Luke, et al.
Pubblicazione: (2024)

Asymmetric Phase Diagrams, Algebraically Ordered BKT Phase, and Peninsular Potts Flow Structure in Long-Range Spin Glasses
di: Gurleyen, S. Efe, et al.
Pubblicazione: (2021)

Dataset-learning duality and emergent criticality
di: Kukleva, Ekaterina, et al.
Pubblicazione: (2024)

Thermodynamics of bidirectional associative memories
di: Barra, Adriano, et al.
Pubblicazione: (2022)

Transition path sampling in Ising models on heterogeneous graphs
di: Cipolloni, Riccardo, et al.
Pubblicazione: (2026)

Impact of ChatGPT on the writing style of condensed matter physicists
di: Xu, Shaojun, et al.
Pubblicazione: (2024)

Fermi-Bose Machine achieves both generalization and adversarial robustness
di: Xie, Mingshan, et al.
Pubblicazione: (2024)

The Copycat Perceptron: Smashing Barriers Through Collective Learning
di: Catania, Giovanni, et al.
Pubblicazione: (2023)

The autoregressive neural network architecture of the Boltzmann distribution of pairwise interacting spins systems
di: Biazzo, Indaco
Pubblicazione: (2023)

Universal Scaling Laws of Absorbing Phase Transitions in Artificial Deep Neural Networks
di: Tamai, Keiichi, et al.
Pubblicazione: (2023)

Explaining the effects of non-convergent sampling in the training of Energy-Based Models
di: Agoritsas, Elisabeth, et al.
Pubblicazione: (2023)

Sampling with flows, diffusion and autoregressive neural networks: A spin-glass perspective
di: Ghio, Davide, et al.
Pubblicazione: (2023)

Stochastic Gradient Descent-like relaxation is equivalent to Metropolis dynamics in discrete optimization and inference problems
di: Angelini, Maria Chiara, et al.
Pubblicazione: (2023)

Inferring effective couplings with Restricted Boltzmann Machines
di: Decelle, Aurélien, et al.
Pubblicazione: (2023)

Weight fluctuations in (deep) linear neural networks and a derivation of the inverse-variance flatness relation
di: Gross, Markus, et al.
Pubblicazione: (2023)

Analytic theory of dropout regularization
di: Mori, Francesco, et al.
Pubblicazione: (2025)

Fundamental operating regimes, hyper-parameter fine-tuning and glassiness: towards an interpretable replica-theory for trained restricted Boltzmann machines
di: Fachechi, Alberto, et al.
Pubblicazione: (2024)

Interpreting the Synchronization Gap: The Hidden Mechanism Inside Diffusion Transformers
di: Albrychiewicz, Emil, et al.
Pubblicazione: (2026)

Optimal Protocols for Continual Learning via Statistical Physics and Control Theory
di: Mori, Francesco, et al.
Pubblicazione: (2024)

Inferring Higher-Order Couplings with Neural Networks
di: Decelle, Aurélien, et al.
Pubblicazione: (2025)

Escape dynamics and implicit bias of one-pass SGD in overparameterized quadratic networks
di: Bocchi, Dario, et al.
Pubblicazione: (2026)

From Classical to Quantum: Extending Prometheus for Unsupervised Discovery of Phase Transitions in Three Dimensions and Quantum Systems
di: Yee, Brandon, et al.
Pubblicazione: (2026)

Transfer Learning in $\ell_1$ Regularized Regression: Hyperparameter Selection Strategy based on Sharp Asymptotic Analysis
di: Okajima, Koki, et al.
Pubblicazione: (2024)