Copertina

Thermodynamic Isomorphism of Transformers: A Lagrangian Approach to Attention Dynamics

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Kim, Gunn
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Statistical Mechanics
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Non-Equilibrium Stochastic Dynamics as a Unified Framework for Insight and Repetitive Learning: A Kramers Escape Approach to Continual Learning
di: Kim, Gunn
Pubblicazione: (2026)

Thermodynamic Optimization of Sensory Adaptation via Game-Theoretic Path Integrals
di: Kim, Gunn
Pubblicazione: (2026)

Scaling Autoregressive Models for Lattice Thermodynamics
di: Du, Xiaochen, et al.
Pubblicazione: (2026)

Solvation Free Energies from Neural Thermodynamic Integration
di: Máté, Bálint, et al.
Pubblicazione: (2024)

Thermodynamic Performance Limits for Score-Based Diffusion Models
di: Kodama, Nathan X., et al.
Pubblicazione: (2025)

Neural Thermodynamic Integration: Free Energies from Energy-based Diffusion Models
di: Máté, Bálint, et al.
Pubblicazione: (2024)

Thermodynamic Bayesian Inference
di: Aifer, Maxwell, et al.
Pubblicazione: (2024)

Capturing the Topological Phase Transition and Thermodynamics of the 2D XY Model via Manifold-Aware Score-Based Generative Modeling
di: Jha, Pratyush
Pubblicazione: (2026)

Thermodynamic Irreversibility of Training Algorithms
di: Ziyin, Liu, et al.
Pubblicazione: (2026)

The Thermodynamic Costs of Simple Linear Regression
di: D'Ambrosia, Samuel H., et al.
Pubblicazione: (2026)

Dynamical Regimes of Diffusion Models
di: Biroli, Giulio, et al.
Pubblicazione: (2024)

Efficient Identification of Critical Transitions via Flow Matching: A Scalable Generative Approach for Many-Body Systems
di: Lee, Qian-Rui, et al.
Pubblicazione: (2025)

Learning the Intrinsic Dimensionality of Fermi-Pasta-Ulam-Tsingou Trajectories: A Nonlinear Approach using a Deep Autoencoder Model
di: Marchetti, Gionni
Pubblicazione: (2026)

Steering Dynamical Regimes of Diffusion Models by Breaking Detailed Balance
di: Lu, Haiqi, et al.
Pubblicazione: (2026)

Combining Reinforcement Learning and Tensor Networks, with an Application to Dynamical Large Deviations
di: Gillman, Edward, et al.
Pubblicazione: (2022)

Critical Scaling and Metabolic Regulation in a Ginzburg--Landau Theory of Cognitive Dynamics
di: Kim, Gunn
Pubblicazione: (2026)

Dynamical symmetries in the fluctuation-driven regime: an application of Noether's theorem to noisy dynamical systems
di: Vastola, John J.
Pubblicazione: (2025)

Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers
di: Tiberi, Lorenzo, et al.
Pubblicazione: (2024)

A Likelihood Approach for Inference of Population Heterogeneity in Particle Ensembles with Second-Order Langevin Dynamics
di: Albrecht, Jan, et al.
Pubblicazione: (2024)

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

Information-Geometric Decomposition of Generalization Error in Unsupervised Learning
di: Kim, Gilhan
Pubblicazione: (2026)

A differentiable programming framework for spin models
di: Farias, Tiago de Souza, et al.
Pubblicazione: (2023)

Beyond Explained Variance: A Cautionary Tale of PCA
di: Marchetti, Gionni
Pubblicazione: (2026)

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

SETOL: A Semi-Empirical Theory of (Deep) Learning
di: Martin, Charles H, et al.
Pubblicazione: (2025)

A Planning-and-Exploring Approach to Extreme-Mechanics Force Fields
di: Shi, Pengjie, et al.
Pubblicazione: (2023)

Symmetry and Generalisation in Neural Approximations of Renormalisation Transformations
di: Ashworth, Cassidy, et al.
Pubblicazione: (2025)

Neural-network quantum state study of the long-range antiferromagnetic Ising chain
di: Kim, Jicheol, et al.
Pubblicazione: (2023)

Ridge Regression from Poisson Resetting: A Renewal Perspective on Spectral Regularization
di: Jolakoski, Petar
Pubblicazione: (2026)

Topological Reorganization and Coordination-Controlled Crossover in Synchronization Onset on Regular Lattices
di: Kim, Gunn
Pubblicazione: (2026)

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

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

Laws of thermodynamics for exponential families
di: Balsubramani, Akshay
Pubblicazione: (2025)

Improving FMQA via Initial Training Data Design Considering Marginal Bit Coverage in One-Hot Encoding
di: Hayashi, Taiga, et al.
Pubblicazione: (2026)

Posterior Collapse as Automatic Spectral Pruning
di: Hirn, Johannes
Pubblicazione: (2026)

Composing diffusion priors with explicit physical context via generative Gibbs sampling
di: Wang, Weizhou, et al.
Pubblicazione: (2026)

The topological gap at criticality: scaling exponent d + η, universality, and scope
di: Loftus, Matthew
Pubblicazione: (2026)

Selecting Optimal Variable Order in Autoregressive Ising Models
di: Biswal, Shiba, et al.
Pubblicazione: (2026)

Computationally sufficient statistics for Ising models
di: Jayakumar, Abhijith, et al.
Pubblicazione: (2026)

Cross-Spectral Witness for Hidden Nonequilibrium Beyond the Scalar Ceiling
di: Bi, Yuda, et al.
Pubblicazione: (2026)