Global $\mathcal{L}^2$ minimization at uniform exponential rate via geometrically adapted gradient descent in Deep Learning
Fuente:
arXiv
Saved in:
| Main Author: | Chen, Thomas |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
On non-approximability of zero loss global ${\mathcal L}^2$ minimizers by gradient descent in Deep Learning
by: Chen, Thomas, et al.
Published: (2023)
by: Chen, Thomas, et al.
Published: (2023)
Geometric structure of Deep Learning networks and construction of global ${\mathcal L}^2$ minimizers
by: Chen, Thomas, et al.
Published: (2023)
by: Chen, Thomas, et al.
Published: (2023)
Geometric structure of shallow neural networks and constructive ${\mathcal L}^2$ cost minimization
by: Chen, Thomas, et al.
Published: (2023)
by: Chen, Thomas, et al.
Published: (2023)
Derivation of effective gradient flow equations and dynamical truncation of training data in Deep Learning
by: Chen, Thomas
Published: (2025)
by: Chen, Thomas
Published: (2025)
Zero loss guarantees and explicit minimizers for generic overparametrized Deep Learning networks
by: Chen, Thomas, et al.
Published: (2025)
by: Chen, Thomas, et al.
Published: (2025)
Interpretable global minima of deep ReLU neural networks on sequentially separable data
by: Chen, Thomas, et al.
Published: (2024)
by: Chen, Thomas, et al.
Published: (2024)
Architecture independent generalization bounds for overparametrized deep ReLU networks
by: Bapu, Anandatheertha, et al.
Published: (2025)
by: Bapu, Anandatheertha, et al.
Published: (2025)
Singular fibrations over surfaces
by: Funar, Louis
Published: (2022)
by: Funar, Louis
Published: (2022)
On coincidences of Morin and first order Thom--Boardman singular loci
by: Csépai, András, et al.
Published: (2024)
by: Csépai, András, et al.
Published: (2024)
Gradient flow in parameter space is equivalent to linear interpolation in output space
by: Chen, Thomas, et al.
Published: (2024)
by: Chen, Thomas, et al.
Published: (2024)
Relationships Between Necessary Conditions for Feedback Stabilizability
by: Kvalheim, Matthew D.
Published: (2023)
by: Kvalheim, Matthew D.
Published: (2023)
A Riemannian gradient descent method for optimization on the indefinite Stiefel manifold
by: Van Tiep, Dinh, et al.
Published: (2024)
by: Van Tiep, Dinh, et al.
Published: (2024)
Learning non-equilibrium diffusions with Schrödinger bridges: from exactly solvable to simulation-free
by: Zhang, Stephen Y., et al.
Published: (2025)
by: Zhang, Stephen Y., et al.
Published: (2025)
An Invariant for Triple-Point-Free Immersed Spheres
by: Seidel, Jona
Published: (2025)
by: Seidel, Jona
Published: (2025)
An algorithmic discrete gradient field and the cohomology algebra of configuration spaces of two points on complete graphs
by: González, Emilio J., et al.
Published: (2022)
by: González, Emilio J., et al.
Published: (2022)
Conditional Density Estimation, Latent Variable Discovery and Optimal Transport
by: Yang, Hongkang, et al.
Published: (2019)
by: Yang, Hongkang, et al.
Published: (2019)
Characterization of generic parameter families of constraint mappings in optimization
by: Hamada, Naoki, et al.
Published: (2024)
by: Hamada, Naoki, et al.
Published: (2024)
Higher categories of bordisms with geometric structures
by: Grady, Daniel, et al.
Published: (2026)
by: Grady, Daniel, et al.
Published: (2026)
Models Parametric Analysis via Adaptive Kernel Learning
by: Norkin, Vladimir, et al.
Published: (2025)
by: Norkin, Vladimir, et al.
Published: (2025)
Source identification via pathwise gradient estimation
by: Lehoucq, Richard B., et al.
Published: (2025)
by: Lehoucq, Richard B., et al.
Published: (2025)
Quantifying the structural stability of simplicial homology
by: Guglielmi, Nicola, et al.
Published: (2023)
by: Guglielmi, Nicola, et al.
Published: (2023)
Simplifying generic smooth maps to the 2-sphere and to the plane
by: Saeki, Osamu
Published: (2024)
by: Saeki, Osamu
Published: (2024)
Homology concordance and knot Floer homology
by: Dai, Irving, et al.
Published: (2021)
by: Dai, Irving, et al.
Published: (2021)
A control-oriented approach to optimal sensor placement
by: Madhavan, Madhusudan, et al.
Published: (2025)
by: Madhavan, Madhusudan, et al.
Published: (2025)
Stability of the persistence transformation
by: Klaila, Gideon, et al.
Published: (2023)
by: Klaila, Gideon, et al.
Published: (2023)
Reconstruction of unknown monotone nonlinear operators in semilinear elliptic models using optimal inputs
by: Bartsch, Jan, et al.
Published: (2024)
by: Bartsch, Jan, et al.
Published: (2024)
Two-bridge links and stable maps into the plane
by: Ichihara, Kazuhiro, et al.
Published: (2024)
by: Ichihara, Kazuhiro, et al.
Published: (2024)
On a construction of stable maps from 3-manifolds into surfaces
by: Kato, Gakuto
Published: (2025)
by: Kato, Gakuto
Published: (2025)
Variational integrators for optimal control of foldable drones
by: Colombo, L., et al.
Published: (2025)
by: Colombo, L., et al.
Published: (2025)
The Chordal Distance Transform of Geometric Loops and its Persistent Homology
by: Binnie, James A. D., et al.
Published: (2026)
by: Binnie, James A. D., et al.
Published: (2026)
Grafos pesados y aplicaciones estables de 3-variedades en R 3
by: Nelson B. Huamaní
Published: (2021)
by: Nelson B. Huamaní
Published: (2021)
Hierarchical threshold structure in Max-Cut with geometric edge weights
by: Marić, Nevena
Published: (2026)
by: Marić, Nevena
Published: (2026)
Equivariant trisections for group actions on four-manifolds
by: Meier, Jeffrey, et al.
Published: (2025)
by: Meier, Jeffrey, et al.
Published: (2025)
Jacobi algebroids and Jacobi sigma models
by: Di Cosmo, Fabio, et al.
Published: (2024)
by: Di Cosmo, Fabio, et al.
Published: (2024)
A Machine Learning Method for Stackelberg Mean Field Games
by: Dayanikli, Gokce, et al.
Published: (2023)
by: Dayanikli, Gokce, et al.
Published: (2023)
Momentum-based gradient descent methods for Lie groups
by: Campos, Cédric M., et al.
Published: (2024)
by: Campos, Cédric M., et al.
Published: (2024)
On hidden face contributions of configuration space integrals for long embeddings
by: Yoshioka, Leo
Published: (2024)
by: Yoshioka, Leo
Published: (2024)
Some non-trivial cycles of the space of long embeddings detected by configuration space integral invariants using g-loop (g =2, 3) graphs
by: Yoshioka, Leo
Published: (2025)
by: Yoshioka, Leo
Published: (2025)
Cocycles of the space of long embeddings and BCR graphs with more than one loop
by: Yoshioka, Leo
Published: (2022)
by: Yoshioka, Leo
Published: (2022)
Constraint Qualification for Generic Parameter Families of Constraints in Optimization
by: Hamada, Naoki, et al.
Published: (2025)
by: Hamada, Naoki, et al.
Published: (2025)
Similar Items
-
On non-approximability of zero loss global ${\mathcal L}^2$ minimizers by gradient descent in Deep Learning
by: Chen, Thomas, et al.
Published: (2023) -
Geometric structure of Deep Learning networks and construction of global ${\mathcal L}^2$ minimizers
by: Chen, Thomas, et al.
Published: (2023) -
Geometric structure of shallow neural networks and constructive ${\mathcal L}^2$ cost minimization
by: Chen, Thomas, et al.
Published: (2023) -
Derivation of effective gradient flow equations and dynamical truncation of training data in Deep Learning
by: Chen, Thomas
Published: (2025) -
Zero loss guarantees and explicit minimizers for generic overparametrized Deep Learning networks
by: Chen, Thomas, et al.
Published: (2025)