Cover Image

Overparameterization of deep ResNet: zero loss and mean-field analysis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ding, Zhiyan, Chen, Shi, Li, Qin, Wright, Stephen
Format:	Preprint
Published:	2021
Subjects:	Machine Learning Numerical Analysis
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Approximation theory for 1-Lipschitz ResNets
by: Murari, Davide, et al.
Published: (2025)

Invertible ResNets for Inverse Imaging Problems: Competitive Performance with Provable Regularization Properties
by: Arndt, Clemens, et al.
Published: (2024)

Constrained Ensemble Langevin Monte Carlo
by: Ding, Zhiyan, et al.
Published: (2021)

Ensemble Kalman Sampler: mean-field limit and convergence analysis
by: Ding, Zhiyan, et al.
Published: (2019)

Ensemble Kalman Inversion: mean-field limit and convergence analysis
by: Ding, Zhiyan, et al.
Published: (2019)

Anisotropic Diffusion Stencils: From Simple Derivations over Stability Estimates to ResNet Implementations
by: Schrader, Karl, et al.
Published: (2023)

Bayesian sampling using interacting particles
by: Chen, Shi, et al.
Published: (2024)

Weighted quantization using MMD: From mean field to mean shift via gradient flows
by: Belhadji, Ayoub, et al.
Published: (2025)

Efficiently Solving High-Order and Nonlinear ODEs with Rational Fraction Polynomial: the Ratio Net
by: Qin, Chenxin, et al.
Published: (2021)

Branch Scaling Manifests as Implicit Architectural Regularization for Improving Generalization in Overparameterized ResNets
by: Yu, Zixiong, et al.
Published: (2024)

On the expressivity of deep Heaviside networks
by: Kong, Insung, et al.
Published: (2025)

Parametric model reduction of mean-field and stochastic systems via higher-order action matching
by: Berman, Jules, et al.
Published: (2024)

PirateNets: Physics-informed Deep Learning with Residual Adaptive Networks
by: Wang, Sifan, et al.
Published: (2024)

A reduced order Schwarz method for nonlinear multiscale elliptic equations based on two-layer neural networks
by: Chen, Shi, et al.
Published: (2021)

Ensemble Kalman Inversion for nonlinear problems: weights, consistency, and variance bounds
by: Ding, Zhiyan, et al.
Published: (2020)

Structure and asymptotic preserving deep neural surrogates for uncertainty quantification in multiscale kinetic equations
by: Chen, Wei, et al.
Published: (2025)

DPG loss functions for learning parameter-to-solution maps by neural networks
by: Castillo, Pablo Cortés, et al.
Published: (2025)

Universal approximation property of ODENet and ResNet with a single activation function
by: Kimura, Masato, et al.
Published: (2024)

ChebNet: Efficient and Stable Constructions of Deep Neural Networks with Rectified Power Units via Chebyshev Approximations
by: Tang, Shanshan, et al.
Published: (2019)

Resolution invariant deep operator network for PDEs with complex geometries
by: Huang, Jianguo, et al.
Published: (2024)

Mesh motion in fluid-structure interaction with deep operator networks
by: Hellan, Ottar
Published: (2024)

Optimal deep learning of holomorphic operators between Banach spaces
by: Adcock, Ben, et al.
Published: (2024)

Towards Size-Independent Generalization Bounds for Deep Operator Nets
by: Gopalani, Pulkit, et al.
Published: (2022)

Robust Fuzzy local k-plane clustering with mixture distance of hinge loss and L1 norm
by: Huang, Junjun, et al.
Published: (2026)

Streaming Krylov-Accelerated Stochastic Gradient Descent
by: Thomas, Stephen
Published: (2025)

Kernel-based potential mean-field games with unbiased random Fourier $U$-statistics
by: Nakano, Yumiharu
Published: (2026)

A novel data generation scheme for surrogate modelling with deep operator networks
by: Choubey, Shivam, et al.
Published: (2024)

Memorization capacity of deep ReLU neural networks characterized by width and depth
by: Yang, Xin, et al.
Published: (2026)

Low-rank computation of the posterior mean in Multi-Output Gaussian Processes
by: Esche, Sebastian, et al.
Published: (2025)

Solving the Wide-band Inverse Scattering Problem via Equivariant Neural Networks
by: Zhang, Borong, et al.
Published: (2022)

On the optimal approximation of Sobolev and Besov functions using deep ReLU neural networks
by: Yang, Yunfei
Published: (2024)

Learning smooth functions in high dimensions: from sparse polynomials to deep neural networks
by: Adcock, Ben, et al.
Published: (2024)

Approximation and learning of anisotropic and mixed smooth functions by deep ReLU neural networks
by: Yang, Yunfei, et al.
Published: (2026)

Convergence of two-timescale gradient descent ascent dynamics: finite-dimensional and mean-field perspectives
by: An, Jing, et al.
Published: (2025)

Data-Driven Model Reduction using WeldNet: Windowed Encoders for Learning Dynamics
by: Dahal, Biraj, et al.
Published: (2025)

Convergence analysis of OT-Flow for sample generation
by: Jing, Yang, et al.
Published: (2024)

Evaluation of data driven low-rank matrix factorization for accelerated solutions of the Vlasov equation
by: Jonnalagadda, Bhavana, et al.
Published: (2024)

Matrix Completion with Cross-Concentrated Sampling: Bridging Uniform Sampling and CUR Sampling
by: Cai, HanQin, et al.
Published: (2022)

Back-Projection Diffusion: Solving the Wideband Inverse Scattering Problem with Diffusion Models
by: Zhang, Borong, et al.
Published: (2024)

Algorithmically Designed Artificial Neural Networks (ADANNs): Higher order deep operator learning for parametric partial differential equations
by: Jentzen, Arnulf, et al.
Published: (2023)