Copertina

SympFormer: Accelerated attention blocks via Inertial Dynamics on Density Manifolds

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Stein, Viktor, Li, Wuchen, Steidl, Gabriele
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Optimization and Control Primary 49Q22, Secondary 37N40, 35Q68, 65P10, 68T07
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Meshless Shape Optimization using Neural Networks and Partial Differential Equations on Graphs
di: Martinet, Eloi, et al.
Pubblicazione: (2025)

A supervised learning scheme for computing Hamilton-Jacobi equation via density coupling
di: Cui, Jianbo, et al.
Pubblicazione: (2024)

Fixed-Point Neural Optimal Transport without Implicit Differentiation
di: Park, Yesom, et al.
Pubblicazione: (2026)

Convergence, design and training of continuous-time dropout as a random batch method
di: Álvarez-López, Antonio, et al.
Pubblicazione: (2025)

Quantitative Convergence of Wasserstein Gradient Flows of Kernel Mean Discrepancies
di: Chizat, Lénaïc, et al.
Pubblicazione: (2026)

No-Regret Generative Modeling via Parabolic Monge-Ampère PDE
di: Deb, Nabarun, et al.
Pubblicazione: (2025)

Training-Induced Escape from Token Clustering in a Mean-Field Formulation of Transformers
di: Isobe, Noboru, et al.
Pubblicazione: (2026)

Implicit Regularization of Large Neural Networks via Mean-Field Formulation
di: Acciaio, Beatrice, et al.
Pubblicazione: (2026)

A First Step Towards Mesh-Free Probabilistic Shape Optimization
di: Schmidt, Stephan, et al.
Pubblicazione: (2026)

Log-Averaged Mirror Prox for Fast, Large-Scale Optimal Transport in Linear Space
di: Burns, Matthew X., et al.
Pubblicazione: (2025)

Cluster-based classification with neural ODEs via control
di: Álvarez-López, Antonio, et al.
Pubblicazione: (2023)

Well-Posed KL-Regularized Control via Wasserstein and Kalman-Wasserstein KL Divergences
di: Stein, Viktor, et al.
Pubblicazione: (2026)

LieDetect: Detection of representation orbits of compact Lie groups from point clouds
di: Ennes, Henrique, et al.
Pubblicazione: (2023)

Monge-Kantorovich Fitting With Sobolev Budgets
di: Kobayashi, Forest, et al.
Pubblicazione: (2024)

Extended Flow Matching: a Method of Conditional Generation with Generalized Continuity Equation
di: Isobe, Noboru, et al.
Pubblicazione: (2024)

An Operator Learning Approach to Nonsmooth Optimal Control of Nonlinear PDEs
di: Song, Yongcun, et al.
Pubblicazione: (2024)

Wasserstein Gradient Flows of MMD Functionals with Distance Kernels under Sobolev Regularization
di: Duong, Richard, et al.
Pubblicazione: (2024)

Sampling Boltzmann distributions via normalizing flow approximation of transport maps
di: Rehman, Zia Ur, et al.
Pubblicazione: (2026)

Score-based deterministic density sampling
di: Ilin, Vasily, et al.
Pubblicazione: (2025)

Variational formulations of ODE-Net as a mean-field optimal control problem and existence results
di: Isobe, Noboru, et al.
Pubblicazione: (2023)

Constrained Optimal Polynomials for Quantum Linear System Solvers
di: Deiml, Matthias, et al.
Pubblicazione: (2026)

A DeepParticle method for learning and generating aggregation patterns in multi-dimensional Keller-Segel chemotaxis systems
di: Wang, Zhongjian, et al.
Pubblicazione: (2022)

Transport based particle methods for the Fokker-Planck-Landau equation
di: Ilin, Vasily, et al.
Pubblicazione: (2024)

Normalization in Attention Dynamics
di: Karagodin, Nikita, et al.
Pubblicazione: (2025)

Machine Learning-based quadratic closures for non-intrusive Reduced Order Models
di: Codega, Gabriele, et al.
Pubblicazione: (2025)

Diffeomorphic Measure Matching with Kernels for Generative Modeling
di: Pandey, Biraj, et al.
Pubblicazione: (2024)

Near-optimal learning of Banach-valued, high-dimensional functions via deep neural networks
di: Adcock, Ben, et al.
Pubblicazione: (2022)

Deep Kuratowski Embedding Neural Networks for Wasserstein Metric Learning
di: He, Andrew Qing
Pubblicazione: (2026)

Teaching and Learning under Deductive Errors
di: Telle, Jan Arne, et al.
Pubblicazione: (2026)

Nonlinear quantum computation by amplified encodings
di: Deiml, Matthias, et al.
Pubblicazione: (2024)

On Immutable Memory Systems for Artificial Agents: A Blockchain-Indexed Automata-Theoretic Framework Using ECDH-Keyed Merkle Chains
di: Wright, Craig Steven
Pubblicazione: (2025)

In-Context Operator Learning on the Space of Probability Measures
di: Cole, Frank, et al.
Pubblicazione: (2026)

Lipschitz-regularized gradient flows and generative particle algorithms for high-dimensional scarce data
di: Gu, Hyemin, et al.
Pubblicazione: (2022)

Visualizing Shape Functionals via Sinkhorn Multidimensional Scaling
di: Yachimura, Toshiaki, et al.
Pubblicazione: (2024)

Learning Neural Pushforward Samplers for Distributions from Fokker-Planck Equations by Weak Adversarial Training
di: He, Andrew Qing, et al.
Pubblicazione: (2025)

Computational homogenization for aerogel-like polydisperse open-porous materials using neural network--based surrogate models on the microscale
di: Klawonn, Axel, et al.
Pubblicazione: (2024)

ADAPT: Lightweight, Long-Range Machine Learning Force Fields Without Graphs
di: Dramko, Evan, et al.
Pubblicazione: (2025)

Graph-Informed Adversarial Modeling: Infimal Subadditivity of Interpolative Divergences
di: Birmpa, Panagiota, et al.
Pubblicazione: (2026)

Retraction based regression methods on Riemannian manifolds
di: Loayza-Romero, Estefanía, et al.
Pubblicazione: (2026)

Computational Complexity of Minimal Trap Spaces in Boolean Networks
di: Moon, Kyungduk, et al.
Pubblicazione: (2022)