paper-with-me

홈 › Papers

Towards an Understanding of Residual Networks Using Neural Tangent Hierarchy (NTH)

2020-07-07 · Yuqing Li, Tao Luo, Nung Kwan Yip

Gradient descent yields zero training loss in polynomial time for deep neural networks despite non-convex nature of the objective function. The behavior of network in the infinite width limit trained by gradient descent can be described by the Neural Tangent Kernel (NTK) introduced in \cite{Jacot2018Neural}. In this paper, we study dynamics of the NTK for finite width Deep Residual Network (ResNet) using the neural tangent hierarchy (NTH) proposed in \cite{Huang2019Dynamics}. For a ResNet with smooth and Lipschitz activation function, we reduce the requirement on the layer width $m$ with respect to the number of training samples $n$ from quartic to cubic. Our analysis suggests strongly that the particular skip-connection structure of ResNet is the main reason for its triumph over fully-connected network.

📄 PDF Abstract BibTeX arXiv:2007.03714

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

NTK 설명 없음
Kaiming Initialization 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Average Pooling 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Batch Normalization 설명 없음
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Dynamics of Deep Neural Networks and Neural Tangent Hierarchy

2019-09-18 · ICML 2020 1 · Jiaoyang Huang, Horng-Tzer Yau

The evolution of a deep neural network trained by the gradient descent can be described by its neural tangent kernel (NTK) as introduced in [20], where it was proven that in the infinite width limit the NTK converges to …

regression

Hyperbolic Residual Quantization: Discrete Representations for Data with Latent Hierarchies

2025-05-18 · Piotr Piękos, Subhradeep Kayal, Alexandros Karatzoglou

Hierarchical data arise in countless domains, from biological taxonomies and organizational charts to legal codes and knowledge graphs. Residual Quantization (RQ) is widely used to generate discrete, multitoken represent…

Inductive BiasKnowledge GraphsQuantizationRepresentation Learning

Spectral Analysis of the Neural Tangent Kernel for Deep Residual Networks

2021-04-07 · Yuval Belfer, Amnon Geifman, Meirav Galun, Ronen Basri

Deep residual network architectures have been shown to achieve superior accuracy over classical feed-forward networks, yet their success is still not fully understood. Focusing on massively over-parameterized, fully conn…

Mathematical Foundations of Neural Tangents and Infinite-Width Networks

2025-12-09 · Rachana Mysore, Preksha Girish, Kavitha Jayaram, Shrey Kumar 외 arxiv

We investigate the mathematical foundations of neural networks in the infinite-width regime through the Neural Tangent Kernel (NTK). We propose the NTK-Eigenvalue-Controlled Residual Network (NTK-ECRN), an architecture i…

MotionPyramid: Hierarchical Motion Representation and Residual Interfaces

2026-06-15 · Gao Zhu, Zaishuo Xia, Yubei Chen arxiv

We ask whether the representational hierarchy seen in perception, from local primitives such as edges to higher level structures such as parts and objects, can be established for motion. In humanoid control, low level ac…

Reinforcement Learning