Nonlinear Weighted Directed Acyclic Graph and A Priori Estimates for Neural Networks

2021-03-30 · Yuqing Li, Tao Luo, Chao Ma

In an attempt to better understand structural benefits and generalization power of deep neural networks, we firstly present a novel graph theoretical formulation of neural network models, including fully connected, residual network (ResNet) and densely connected networks (DenseNet). Secondly, we extend the error analysis of the population risk for two layer network \cite{ew2019prioriTwo} and ResNet \cite{e2019prioriRes} to DenseNet, and show further that for neural networks satisfying certain mild conditions, similar estimates can be obtained. These estimates are a priori in nature since they depend sorely on the information prior to the training process, in particular, the bounds for the estimation errors are independent of the input dimension.

📄 PDF Abstract BibTeX arXiv:2103.16355

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Residual Connection 설명 없음

Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…

Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…

Batch Normalization 설명 없음

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

A Framework for Directed Acyclic Hypergraph Learning

2026-06-19 · Zhiyuan Dong, Carlos Mundo-Levano, Wei Qian, Daniel Lau 외 arxiv

Continuous optimization methods for learning Directed Acyclic Graphs (DAGs) operate on weighted adjacency matrices and are therefore limited to pairwise causal relationships. We propose a framework for learning Directed …

Similar Formation Control of Multi-Agent Systems over Directed Acyclic Graphs via Matrix-Weighted Laplacian

2025-06-14 · Zhipeng Fan, Yujie Xu, Mingyu Fu, Han Sun 외

This brief proposes a distributed formation control strategy via matrix-weighted Laplacian that can achieve a similar formation in 2-D planar using inter-agent relative displacement measurement. Formation patterns that i…

Generalized Priority-Aware Shapley Value

2026-05-14 · Kiljae Lee, Ziqi Liu, Weijing Tang, Yuan Zhang arxiv

Shapley value and its priority-aware extensions are widely used for valuation in machine learning, but existing methods require pairwise priority to be binary and acyclic, a restriction spectacularly violated in real-dat…

Weighted First Order Model Counting with Directed Acyclic Graph Axioms

2023-02-20 · Sagar Malhotra, Luciano Serafini

Statistical Relational Learning (SRL) integrates First-Order Logic (FOL) and probability theory for learning and inference over relational data. Probabilistic inference and learning in many SRL models can be reduced to W…

Relational Reasoning

Stable Causal Discovery via Directed Acyclic Graph Aggregation

2026-05-18 · Yunan Wu, Yue Wang, Chunlin Li, Chenglong Ye arxiv

Directed Acyclic Graphs (DAGs) are central to uncovering causal structure in complex systems, yet learning a single DAG from data is often challenging: model uncertainty, finite samples, and a combinatorially large searc…