Exploring Neural Network Landscapes: Star-Shaped and Geodesic Connectivity

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Zhanran, Li, Puheng, Wu, Lei
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Analyzing the Role of Permutation Invariance in Linear Mode Connectivity
by: Zhan, Keyao, et al.
Published: (2025)

FaiREE: Fair Classification with Finite-Sample and Distribution-Free Guarantee
by: Li, Puheng, et al.
Published: (2022)

Robust Sampling for Active Statistical Inference
by: Li, Puheng, et al.
Published: (2025)

Connecting Neural Models Latent Geometries with Relative Geodesic Representations
by: Yu, Hanlin, et al.
Published: (2025)

On the Generalization Properties of Diffusion Models
by: Li, Puheng, et al.
Published: (2023)

Riemannian Neural Geodesic Interpolant
by: Wu, Jiawen, et al.
Published: (2025)

FedGuCci: Making Local Models More Connected in Landscape for Federated Learning
by: Li, Zexi, et al.
Published: (2024)

Landscaping Linear Mode Connectivity
by: Singh, Sidak Pal, et al.
Published: (2024)

Learning Relativistic Geodesics and Chaotic Dynamics via Stabilized Lagrangian Neural Networks
by: Hamzaogullari, Abdullah Umut, et al.
Published: (2026)

Visualizing, Rethinking, and Mining the Loss Landscape of Deep Neural Networks
by: Xu, Yichu, et al.
Published: (2024)

Neural Network-based High-index Saddle Dynamics Method for Searching Saddle Points and Solution Landscape
by: Liu, Yuankai, et al.
Published: (2024)

CHORDS: Diffusion Sampling Accelerator with Multi-core Hierarchical ODE Solvers
by: Han, Jiaqi, et al.
Published: (2025)

Visualization and Analysis of the Loss Landscape in Graph Neural Networks
by: Moustafa, Samir, et al.
Published: (2025)

A VAE-based Framework for Learning Multi-Level Neural Granger-Causal Connectivity
by: Lin, Jiahe, et al.
Published: (2024)

Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding
by: Wu, Frank Zhengqing, et al.
Published: (2024)

Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy
by: Shaik, Thanveer, et al.
Published: (2023)

Differential Equation Scaling Limits of Shaped and Unshaped Neural Networks
by: Li, Mufan Bill, et al.
Published: (2023)

Super Consistency of Neural Network Landscapes and Learning Rate Transfer
by: Noci, Lorenzo, et al.
Published: (2024)

Exploring and Exploiting the Asymmetric Valley of Deep Neural Networks
by: Li, Xin-Chun, et al.
Published: (2024)

Unveiling Mode Connectivity in Graph Neural Networks
by: Li, Bingheng, et al.
Published: (2025)

SLOPE: Optimistic Potential Landscape Shaping for Model-based Reinforcement Learning
by: Li, Yao-Hui, et al.
Published: (2026)

FAGC:Feature Augmentation on Geodesic Curve in the Pre-Shape Space
by: Han, Yuexing, et al.
Published: (2023)

Guided Star-Shaped Masked Diffusion
by: Meshchaninov, Viacheslav, et al.
Published: (2025)

Geodesics in the Deep Linear Network
by: Chen, Alan
Published: (2025)

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

Mathematical Modeling and Convergence Analysis of Deep Neural Networks with Dense Layer Connectivities in Deep Learning
by: Huang, Jinshu, et al.
Published: (2025)

(Deep) Generative Geodesics
by: Kim, Beomsu, et al.
Published: (2024)

A Unified Theory of Quantum Neural Network Loss Landscapes
by: Anschuetz, Eric R.
Published: (2024)

Loss Landscape Characterization of Neural Networks without Over-Parametrization
by: Islamov, Rustem, et al.
Published: (2024)

Linear Mode Connectivity in Sparse Neural Networks
by: McDermott, Luke, et al.
Published: (2023)

From Baselines to Transport Geodesics: Axiomatic Attribution via Optimal Generative Flows
by: Zhang, Cenwei, et al.
Published: (2026)

Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration
by: Han, Jiaqi, et al.
Published: (2026)

Exploring Non-Convex Discrete Energy Landscapes: An Efficient Langevin-Like Sampler with Replica Exchange
by: Zheng, Haoyang, et al.
Published: (2025)

Theoretical Learning Performance of Graph Neural Networks: The Impact of Jumping Connections and Layer-wise Sparsification
by: Sun, Jiawei, et al.
Published: (2025)

Robust and Efficient Deep Hedging via Linearized Objective Neural Network
by: Zhao, Lei, et al.
Published: (2025)

Explainable Graph Neural Networks: Understanding Brain Connectivity and Biomarkers in Dementia
by: Tewari, Niharika, et al.
Published: (2025)

Proving Linear Mode Connectivity of Neural Networks via Optimal Transport
by: Ferbach, Damien, et al.
Published: (2023)

Probabilistic Skip Connections for Deterministic Uncertainty Quantification in Deep Neural Networks
by: Jimenez, Felix, et al.
Published: (2025)

Differentially Private Geodesic Regression
by: Kulkarni, Aditya, et al.
Published: (2025)

Fréchet Geodesic Boosting
by: Zhou, Yidong, et al.
Published: (2025)