Cover Image

Uncovering Critical Sets of Deep Neural Networks via Sample-Independent Critical Lifting

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Leyang, Zhang, Yaoyu, Luo, Tao
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Geometry of Critical Sets and Existence of Saddle Branches for Two-layer Neural Networks
by: Zhang, Leyang, et al.
Published: (2024)

Geometry and Local Recovery of Global Minima of Two-layer Neural Networks at Overparameterization
by: Zhang, Leyang, et al.
Published: (2023)

Local Linear Recovery Guarantee of Deep Neural Networks at Overparameterization
by: Zhang, Yaoyu, et al.
Published: (2024)

Linear Independence of Generalized Neurons and Related Functions
by: Zhang, Leyang
Published: (2024)

Embedding Principle in Depth for the Loss Landscape Analysis of Deep Neural Networks
by: Bai, Zhiwei, et al.
Published: (2022)

Embedding principle of homogeneous neural network for classification problem
by: Zhang, Jiahan, et al.
Published: (2025)

Anomaly Detection Based on Critical Paths for Deep Neural Networks
by: Zhao, Fangzhen, et al.
Published: (2025)

Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing
by: Zhang, Zhongwang, et al.
Published: (2024)

Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks
by: Xu, Zhi-Qin John, et al.
Published: (2019)

CARL: Criticality-Aware Agentic Reinforcement Learning
by: Shen, Leyang, et al.
Published: (2025)

Critical Organization of Deep Neural Networks, and p-Adic Statistical Field Theories
by: Zúñiga-Galindo, W. A.
Published: (2026)

Overview frequency principle/spectral bias in deep learning
by: Xu, Zhi-Qin John, et al.
Published: (2022)

Disentangle Sample Size and Initialization Effect on Perfect Generalization for Single-Neuron Target
by: Zhao, Jiajie, et al.
Published: (2024)

Adaptive Federated LoRA in Heterogeneous Wireless Networks with Independent Sampling
by: Hou, Yanzhao, et al.
Published: (2025)

Adaptive Federated Learning in Heterogeneous Wireless Networks with Independent Sampling
by: Geng, Jiaxiang, et al.
Published: (2024)

Equally Critical: Samples, Targets, and Their Mappings in Datasets
by: Yang, Runkang, et al.
Published: (2025)

A Critical Review of Predominant Bias in Neural Networks
by: Li, Jiazhi, et al.
Published: (2025)

On the Occurence of Critical Learning Periods in Neural Networks
by: Pawlak, Stanisław
Published: (2025)

Beyond Over-smoothing: Uncovering the Trainability Challenges in Deep Graph Neural Networks
by: Peng, Jie, et al.
Published: (2024)

Actor-Critic with Active Importance Sampling
by: Molaei, Majid, et al.
Published: (2026)

Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning
by: Zhang, Zhiyao, et al.
Published: (2025)

Criticality and Saturation in Orthogonal Neural Networks
by: Guillen, Max, et al.
Published: (2026)

Neural Force Field: Few-shot Learning of Generalized Physical Reasoning
by: Li, Shiqian, et al.
Published: (2025)

Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptive Residual Module
by: Zhou, Jingbo, et al.
Published: (2023)

Predicting Critical Heat Flux with Uncertainty Quantification and Domain Generalization Using Conditional Variational Autoencoders and Deep Neural Networks
by: Alsafadi, Farah, et al.
Published: (2024)

Relative Importance Sampling for off-Policy Actor-Critic in Deep Reinforcement Learning
by: Humayoo, Mahammad, et al.
Published: (2018)

Conjugate Learning Theory: Uncovering the Mechanisms of Trainability and Generalization in Deep Neural Networks
by: Qi, Binchuan
Published: (2026)

Ranked Set Sampling-Based Multilayer Perceptron: Improving Generalization via Variance-Based Bounds
by: Li, Feijiang, et al.
Published: (2025)

D2 Actor Critic: Diffusion Actor Meets Distributional Critic
by: Zhang, Lunjun, et al.
Published: (2025)

MAGDiff: Covariate Data Set Shift Detection via Activation Graphs of Deep Neural Networks
by: Arnal, Charles, et al.
Published: (2023)

Closing the Gap: Achieving Global Convergence (Last Iterate) of Actor-Critic under Markovian Sampling with Neural Network Parametrization
by: Gaur, Mudit, et al.
Published: (2024)

Deep Actor-Critics with Tight Risk Certificates
by: Tasdighi, Bahareh, et al.
Published: (2025)

SEED: Targeted Data Selection by Weighted Independent Set
by: Zhang, Yuan, et al.
Published: (2026)

Doubly Robust Conditional Independence Testing with Generative Neural Networks
by: Zhang, Yi, et al.
Published: (2024)

One Period to Rule Them All: Identifying Critical Learning Periods in Deep Networks
by: Fukase, Vinicius Yuiti, et al.
Published: (2025)

Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL
by: Luo, Yu, et al.
Published: (2024)

Set-Valued Sensitivity Analysis of Deep Neural Networks
by: Wang, Xin, et al.
Published: (2024)

The Enduring Dominance of Deep Neural Networks: A Critical Analysis of the Fundamental Limitations of Quantum Machine Learning and Spiking Neural Networks
by: Ishikawa, Takehiro
Published: (2025)

APEX: Probing Neural Networks via Activation Perturbation
by: Ren, Tao, et al.
Published: (2026)

Critical Sampling for Robust Evolution Operator Learning of Unknown Dynamical Systems
by: Zhang, Ce, et al.
Published: (2023)