Copertina

Inexact calculus of variations on the hyperspherical tangent bundle and its connections to the attention mechanism

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Gracyk, Andrew
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Complex variational autoencoders admit Kähler structure
di: Gracyk, Andrew
Pubblicazione: (2025)

Ricci flow regularization in latent spaces for the forward learning of partial differential equations
di: Gracyk, Andrew
Pubblicazione: (2024)

Complex normalizing flows can almost be information Kähler-Ricci flows
di: Gracyk, Andrew
Pubblicazione: (2026)

Pseudo-differential-enhanced physics-informed neural networks
di: Gracyk, Andrew
Pubblicazione: (2026)

Variational autoencoders with latent high-dimensional steady geometric flows for dynamics
di: Gracyk, Andrew
Pubblicazione: (2024)

Observability conditions for neural state-space models with eigenvalues and their roots of unity
di: Gracyk, Andrew
Pubblicazione: (2025)

GeONet: a neural operator for learning the Wasserstein geodesic
di: Gracyk, Andrew, et al.
Pubblicazione: (2022)

Synchronization-based clustering on the unit hypersphere
di: Kapić, Zinaid, et al.
Pubblicazione: (2026)

Geometric flow regularization in latent spaces for smooth dynamics with the efficient variations of curvature
di: Gracyk, Andrew
Pubblicazione: (2025)

Easy attention: A simple attention mechanism for temporal predictions with transformers
di: Sanchis-Agudo, Marcial, et al.
Pubblicazione: (2023)

Approximation of relation functions and attention mechanisms
di: Altabaa, Awni, et al.
Pubblicazione: (2024)

Fast attention mechanisms: a tale of parallelism
di: Liu, Jingwen, et al.
Pubblicazione: (2025)

Relational inductive biases on attention mechanisms
di: Mijangos, Víctor, et al.
Pubblicazione: (2025)

Preconditioned Inexact Stochastic ADMM for Deep Model
di: Zhou, Shenglong, et al.
Pubblicazione: (2025)

Reservoir observer enhanced with residual calibration and attention mechanism
di: Liu, Yichen, et al.
Pubblicazione: (2026)

Tucker Attention: A generalization of approximate attention mechanisms
di: Klein, Timon, et al.
Pubblicazione: (2026)

Inexact subgradient methods for semialgebraic functions
di: Bolte, Jérôme, et al.
Pubblicazione: (2024)

Bilevel Learning with Inexact Stochastic Gradients
di: Salehi, Mohammad Sadegh, et al.
Pubblicazione: (2024)

Rethinking Consistent Multi-Label Classification Under Inexact Supervision
di: Wang, Wei, et al.
Pubblicazione: (2025)

Beyond the Ideal: Analyzing the Inexact Muon Update
di: Shulgin, Egor, et al.
Pubblicazione: (2025)

An Inexact Weighted Proximal Trust-Region Method
di: Maia, Leandro Farias, et al.
Pubblicazione: (2026)

Redundant feature screening method for human activity recognition based on attention purification mechanism
di: Li, Xiaoyang, et al.
Pubblicazione: (2025)

A foundation model with multi-variate parallel attention to generate neuronal activity
di: Carzaniga, Francesco, et al.
Pubblicazione: (2025)

Applications of fractional calculus in learned optimization
di: Szente, Teodor Alexandru, et al.
Pubblicazione: (2024)

Contextual Strongly Convex Simulation Optimization: Optimize then Predict with Inexact Solutions
di: Lin, Nifei, et al.
Pubblicazione: (2025)

Sink vs. diagonal patterns as mechanisms for attention switch and oversmoothing prevention
di: Súkeník, Peter, et al.
Pubblicazione: (2026)

Continual learning with the neural tangent ensemble
di: Benjamin, Ari S., et al.
Pubblicazione: (2024)

Bayesian Optimization with Inexact Acquisition: Is Random Grid Search Sufficient?
di: Kim, Hwanwoo, et al.
Pubblicazione: (2025)

Understanding the role of depth in the neural tangent kernel for overparameterized neural networks
di: St-Arnaud, William, et al.
Pubblicazione: (2025)

Complexity of Inexact Proximal Point Algorithm for minimizing convex functions with Holderian Growth
di: Pătraşcu, Andrei, et al.
Pubblicazione: (2021)

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

Physics-integrated generative modeling using attentive planar normalizing flow based variational autoencoder
di: Akhtar, Sheikh Waqas
Pubblicazione: (2024)

On the Error-Propagation of Inexact Hotelling's Deflation for Principal Component Analysis
di: Liao, Fangshuo, et al.
Pubblicazione: (2023)

Hermitian Yang--Mills connections on general vector bundles: geometry and physical Yukawa couplings
di: Mishra, Challenger, et al.
Pubblicazione: (2025)

Geometric design of the tangent term in landing algorithms for orthogonality constraints
di: Goyens, Florentin, et al.
Pubblicazione: (2025)

Hybrid Deep Learning Model for epileptic seizure classification by using 1D-CNN with multi-head attention mechanism
di: Guhdar, Mohammed, et al.
Pubblicazione: (2025)

A multi-source data power load forecasting method using attention mechanism-based parallel cnn-gru
di: Min, Chao, et al.
Pubblicazione: (2024)

Expressive Power of Floating-Point Neural Networks with Arbitrary Reduction Orders and Inexact Activation Implementations
di: Park, Yeachan, et al.
Pubblicazione: (2026)

Convergence and Complexity Guarantee for Inexact First-order Riemannian Optimization Algorithms
di: Li, Yuchen, et al.
Pubblicazione: (2024)

From Inexact Gradients to Byzantine Robustness: Acceleration and Optimization under Similarity
di: Gaucher, Renaud, et al.
Pubblicazione: (2026)