Cover Image

Attention as In-Context Empirical Bayes: A Two-Stage View via Particle Dynamics

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Smart, Matthew, Ganguly, Soumya, Metya, Nilava, Morozov, Alexandre V., Sengupta, Anirvan M.
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Dynamical Systems
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

In-context denoising with one-layer transformers: connections between attention and associative memory retrieval
by: Smart, Matthew, et al.
Published: (2025)

Understanding Catastrophic Forgetting In LoRA via Mean-Field Attention Dynamics
by: Koubbi, Hugo, et al.
Published: (2024)

Multistability of Self-Attention Dynamics in Transformers
by: Altafini, Claudio
Published: (2025)

Neural Context Flows for Meta-Learning of Dynamical Systems
by: Nzoyem, Roussel Desmond, et al.
Published: (2024)

Teacher Forcing as Generalized Bayes: Optimization Geometry Mismatch in Switching Surrogates for Chaotic Dynamics
by: Herz, Andre, et al.
Published: (2026)

Autoencoding Dynamics: Topological Limitations and Capabilities
by: Kvalheim, Matthew D., et al.
Published: (2025)

Enhancing Neural Training via a Correlated Dynamics Model
by: Brokman, Jonathan, et al.
Published: (2023)

Low-Cost Black-Box Detection of LLM Hallucinations via Dynamical System Prediction
by: Wilson, Dan, et al.
Published: (2026)

Backpropagation on Dynamical Networks
by: Tan, Eugene, et al.
Published: (2022)

Signature Maximum Mean Discrepancy Two-Sample Statistical Tests
by: Alden, Andrew, et al.
Published: (2025)

Dynamics-Informed Deep Learning for Predicting Extreme Events
by: Katsidoniotaki, Eirini, et al.
Published: (2026)

Large-Step Training Dynamics of a Two-Factor Linear Transformer Model
by: Balasubramanian, Krishnakumar
Published: (2026)

Geometry and Local Recovery of Global Minima of Two-layer Neural Networks at Overparameterization
by: Zhang, Leyang, et al.
Published: (2023)

Absence of Closed-Form Descriptions for Gradient Flow in Two-Layer Narrow Networks
by: Park, Yeachan
Published: (2024)

Integrating Multimodal Data for Joint Generative Modeling of Complex Dynamics
by: Brenner, Manuel, et al.
Published: (2022)

Let's do the time-warp-attend: Learning topological invariants of dynamical systems
by: Moriel, Noa, et al.
Published: (2023)

Analysis of tidal flows through the Strait of Gibraltar using Dynamic Mode Decomposition
by: Dias, Sathsara, et al.
Published: (2023)

Weighted Birkhoff Averages Accelerate Data-Driven Methods
by: Bou-Sakr-El-Tayar, Maria, et al.
Published: (2025)

Latent Diffeomorphic Dynamic Mode Decomposition
by: Diepeveen, Willem, et al.
Published: (2025)

Deep Learning of the Evolution Operator Enables Forecasting of Out-of-Training Dynamics in Chaotic Systems
by: Shokar, Ira J. S., et al.
Published: (2025)

PINN-Obs: Physics-Informed Neural Network-Based Observer for Nonlinear Dynamical Systems
by: Farkane, Ayoub, et al.
Published: (2025)

CEBoosting: Online Sparse Identification of Dynamical Systems with Regime Switching by Causation Entropy Boosting
by: Chen, Chuanqi, et al.
Published: (2023)

Learning Deep Dissipative Dynamics
by: Okamoto, Yuji, et al.
Published: (2024)

Continuous-Time Homeostatic Dynamics for Reentrant Inference Models
by: Chae, Byung Gyu
Published: (2025)

Neural Ordinary Differential Equations for Modeling Socio-Economic Dynamics
by: Samota, Sandeep Kumar, et al.
Published: (2026)

Generalized Quadratic Embeddings for Nonlinear Dynamics using Deep Learning
by: Goyal, Pawan, et al.
Published: (2022)

Zero-shot Imputation with Foundation Inference Models for Dynamical Systems
by: Seifner, Patrick, et al.
Published: (2024)

Dynamical systems and complex networks: A Koopman operator perspective
by: Klus, Stefan, et al.
Published: (2024)

Tipping Point Forecasting in Non-Stationary Dynamics on Function Spaces
by: Liu-Schiaffini, Miguel, et al.
Published: (2023)

Deep Recurrent Stochastic Configuration Networks for Modelling Nonlinear Dynamic Systems
by: Dang, Gang, et al.
Published: (2024)

Embedded Variational Neural Stochastic Differential Equations for Learning Heterogeneous Dynamics
by: Samota, Sandeep Kumar, et al.
Published: (2026)

Flowing Through Layers: A Continuous Dynamical Systems Perspective on Transformers
by: Fein-Ashley, Jacob
Published: (2025)

Self-Supervised Evolution Operator Learning for High-Dimensional Dynamical Systems
by: Turri, Giacomo, et al.
Published: (2025)

DySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic Systems
by: Schiff, Yair, et al.
Published: (2024)

A Training-Free Conditional Diffusion Model for Learning Stochastic Dynamical Systems
by: Liu, Yanfang, et al.
Published: (2024)

Cross-Modal Diffusion for Biomechanical Dynamical Systems Through Local Manifold Alignment
by: Dey, Sharmita, et al.
Published: (2025)

ADAM-SINDy: An Efficient Optimization Framework for Parameterized Nonlinear Dynamical System Identification
by: Viknesh, Siva, et al.
Published: (2024)

Neural Ordinary Differential Equations for Learning and Extrapolating System Dynamics Across Bifurcations
by: van Tegelen, Eva, et al.
Published: (2025)

ResKoopNet: Learning Koopman Representations for Complex Dynamics with Spectral Residuals
by: Xu, Yuanchao, et al.
Published: (2025)

A Comparison of Parametric Dynamic Mode Decomposition Algorithms for Thermal-Hydraulics Applications
by: Riva, Stefano, et al.
Published: (2025)