Imagen de Portada

Derivation of effective gradient flow equations and dynamical truncation of training data in Deep Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Chen, Thomas
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence Analysis of PDEs Optimization and Control 57R70, 62M45
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Zero loss guarantees and explicit minimizers for generic overparametrized Deep Learning networks
por: Chen, Thomas, et al.
Publicado: (2025)

Architecture independent generalization bounds for overparametrized deep ReLU networks
por: Bapu, Anandatheertha, et al.
Publicado: (2025)

Global $\mathcal{L}^2$ minimization at uniform exponential rate via geometrically adapted gradient descent in Deep Learning
por: Chen, Thomas
Publicado: (2023)

On non-approximability of zero loss global ${\mathcal L}^2$ minimizers by gradient descent in Deep Learning
por: Chen, Thomas, et al.
Publicado: (2023)

Geometric structure of Deep Learning networks and construction of global ${\mathcal L}^2$ minimizers
por: Chen, Thomas, et al.
Publicado: (2023)

Interpretable global minima of deep ReLU neural networks on sequentially separable data
por: Chen, Thomas, et al.
Publicado: (2024)

Geometric structure of shallow neural networks and constructive ${\mathcal L}^2$ cost minimization
por: Chen, Thomas, et al.
Publicado: (2023)

Reconstruction of unknown monotone nonlinear operators in semilinear elliptic models using optimal inputs
por: Bartsch, Jan, et al.
Publicado: (2024)

Gradient flow in parameter space is equivalent to linear interpolation in output space
por: Chen, Thomas, et al.
Publicado: (2024)

Singular fibrations over surfaces
por: Funar, Louis
Publicado: (2022)

An Equivalence Result on the Order of Differentiability in Frobenius' Theorem
por: Hosoya, Yuhki
Publicado: (2025)

Quantifying the structural stability of simplicial homology
por: Guglielmi, Nicola, et al.
Publicado: (2023)

On coincidences of Morin and first order Thom--Boardman singular loci
por: Csépai, András, et al.
Publicado: (2024)

On some multiple solutions for a $p(x)$-Laplace equation with supercritical growth
por: Zhao, Lin
Publicado: (2024)

$Γ$-convergence involving nonlocal gradients with varying horizon: Recovery of local and fractional models
por: Cueto, Javier, et al.
Publicado: (2024)

Sample Complexity of Quadratically Regularized Optimal Transport
por: González-Sanz, Alberto, et al.
Publicado: (2025)

Identification of source terms in the Schrödinger equation with dynamic boundary conditions from final data
por: Chorfi, Salah-Eddine, et al.
Publicado: (2024)

Nonlocal balance equation: representation and approximation of solution
por: Averboukh, Yurii
Publicado: (2023)

Relationships Between Necessary Conditions for Feedback Stabilizability
por: Kvalheim, Matthew D.
Publicado: (2023)

A control-oriented approach to optimal sensor placement
por: Madhavan, Madhusudan, et al.
Publicado: (2025)

Variational integrators for optimal control of foldable drones
por: Colombo, L., et al.
Publicado: (2025)

Asymptotic compatibility of parametrized optimal design problems
por: Mengesha, Tadele, et al.
Publicado: (2024)

A quasilinear transmission problem with application to Maxwell equations with a divergence-free $\mathcal D$-field
por: Dohnal, Tomáš, et al.
Publicado: (2021)

Clearing-out of dipoles for minimisers of 2-dimensional discrete energies with topological singularities
por: Garroni, Adriana, et al.
Publicado: (2024)

Conjugate harmonic functions in 3D with respect to a unitary gradient
por: Pedregal, Pablo
Publicado: (2025)

Adaptive waveform inversion for transmitted wave data
por: Symes, William W.
Publicado: (2024)

Local convergence of mean-field Langevin dynamics: from gradient flows to linearly monotone games
por: Wang, Guillaume, et al.
Publicado: (2026)

On the required number of electrodes for uniqueness and convex reformulation in an inverse coefficient problem
por: Brojatsch, Andrej, et al.
Publicado: (2024)

Learning non-equilibrium diffusions with Schrödinger bridges: from exactly solvable to simulation-free
por: Zhang, Stephen Y., et al.
Publicado: (2025)

An Invariant for Triple-Point-Free Immersed Spheres
por: Seidel, Jona
Publicado: (2025)

$C^{1,α}$-Regularity of Quasilinear equations on the Heisenberg Group
por: Mukherjee, Shirsho
Publicado: (2018)

An Insensitizing control problem involving tangential gradient terms for a reaction-diffusion equation with dynamic boundary conditions
por: Santos, Mauricio C., et al.
Publicado: (2024)

Sticky-reflecting diffusion as a Wasserstein gradient flow
por: Casteras, Jean-Baptiste, et al.
Publicado: (2024)

An algorithmic discrete gradient field and the cohomology algebra of configuration spaces of two points on complete graphs
por: González, Emilio J., et al.
Publicado: (2022)

Conditional Density Estimation, Latent Variable Discovery and Optimal Transport
por: Yang, Hongkang, et al.
Publicado: (2019)

(Two-scale) $W^{1}L^Φ$-gradient Young measures and homogenization of integral functionals in Orlicz-Sobolev spaces
por: Tachago, Joel Fotso, et al.
Publicado: (2024)

The Mean Field Ensemble Kalman Filter: Near-Gaussian Setting
por: Carrillo, J. A., et al.
Publicado: (2022)

Boundary regularity for subelliptic equations in the Heisenberg group
por: Abedin, Farhan, et al.
Publicado: (2025)

The Wasserstein gradient flow of the Sinkhorn divergence between Gaussian distributions
por: Hardion, Mathis, et al.
Publicado: (2026)

Characterization of generic parameter families of constraint mappings in optimization
por: Hamada, Naoki, et al.
Publicado: (2024)