Latent Point Collapse on a Low Dimensional Embedding in Deep Neural Network Classifiers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Sbailò, Luigi, Ghiringhelli, Luca
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Neural Collapse versus Low-rank Bias: Is Deep Neural Collapse Really Optimal?
di: Súkeník, Peter, et al.
Pubblicazione: (2024)

Latent Communication in Artificial Neural Networks
di: Moschella, Luca
Pubblicazione: (2024)

Optimal Convergence Rates of Deep Neural Network Classifiers
di: Zhang, Zihan, et al.
Pubblicazione: (2025)

Leveraging Intermediate Neural Collapse with Simplex ETFs for Efficient Deep Neural Networks
di: Liu, Emily
Pubblicazione: (2024)

Provable Emergence of Deep Neural Collapse and Low-Rank Bias in $L^2$-Regularized Nonlinear Networks
di: Zangrando, Emanuele, et al.
Pubblicazione: (2024)

Deep Neural Network Calibration by Reducing Classifier Shift with Stochastic Masking
di: Ni, Jiani, et al.
Pubblicazione: (2025)

I Can't Believe It's Not Robust: Catastrophic Collapse of Safety Classifiers under Embedding Drift
di: Sahoo, Subramanyam, et al.
Pubblicazione: (2026)

The Persistence of Neural Collapse Despite Low-Rank Bias
di: Garrod, Connall, et al.
Pubblicazione: (2024)

On the Robustness of Neural Collapse and the Neural Collapse of Robustness
di: Su, Jingtong, et al.
Pubblicazione: (2023)

Provable Accuracy Collapse in Embedding-Based Representations under Dimensionality Mismatch
di: Arvanitakis, Dionysis, et al.
Pubblicazione: (2026)

HOLE: Homological Observation of Latent Embeddings for Neural Network Interpretability
di: Athreya, Sudhanva Manjunath, et al.
Pubblicazione: (2025)

Deep Neural Regression Collapse
di: Rangamani, Akshay, et al.
Pubblicazione: (2026)

Towards Explaining Deep Neural Network Compression Through a Probabilistic Latent Space
di: Mozafari-Nia, Mahsa, et al.
Pubblicazione: (2024)

Layer Embedding Deep Fusion Graph Neural Network
di: Xu, Taihua, et al.
Pubblicazione: (2026)

DEM: A Method for Certifying Deep Neural Network Classifier Outputs in Aerospace
di: Katz, Guy, et al.
Pubblicazione: (2024)

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

Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks
di: Lee, Su Hyeong, et al.
Pubblicazione: (2025)

Training Large Neural Networks With Low-Dimensional Error Feedback
di: Hanut, Maher, et al.
Pubblicazione: (2025)

Learning Low-Dimensional Quadratic-Embeddings of High-Fidelity Nonlinear Dynamics using Deep Learning
di: Goyal, Pawan, et al.
Pubblicazione: (2021)

Emergence of Structure in Ensembles of Random Neural Networks
di: Muscarnera, Luca, et al.
Pubblicazione: (2025)

Neural Mode Jump Monte Carlo
di: Sbailò, Luigi, et al.
Pubblicazione: (2019)

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

Beyond Unconstrained Features: Neural Collapse for Shallow Neural Networks with General Data
di: Hong, Wanli, et al.
Pubblicazione: (2024)

CoBA: Integrated Deep Learning Model for Reliable Low-Altitude UAV Classification in mmWave Radio Networks
di: Sajid, Junaid, et al.
Pubblicazione: (2026)

Navigating the Latent Space Dynamics of Neural Models
di: Fumero, Marco, et al.
Pubblicazione: (2025)

Hard-Negative Sampling for Contrastive Learning: Optimal Representation Geometry and Neural- vs Dimensional-Collapse
di: Jiang, Ruijie, et al.
Pubblicazione: (2023)

Adversarial Attacks and Dimensionality in Text Classifiers
di: Chattopadhyay, Nandish, et al.
Pubblicazione: (2024)

Unifying Low Dimensional Spectra in Deep Learning
di: Garrod, Connall, et al.
Pubblicazione: (2024)

Embedding of Low-Dimensional Sensory Dynamics in Recurrent Networks: Implications for the Geometry of Neural Representation
di: O'Reilly-Shah, Vikas N., et al.
Pubblicazione: (2026)

FTL: Transfer Learning Nonlinear Plasma Dynamic Transitions in Low Dimensional Embeddings via Deep Neural Networks
di: Bai, Zhe, et al.
Pubblicazione: (2024)

Learning Low-Dimensional Embeddings for Black-Box Optimization
di: Busetto, Riccardo, et al.
Pubblicazione: (2025)

How Neural Losses Shape VAE Latents
di: Strano, Giorgio, et al.
Pubblicazione: (2026)

Drug Repurposing Using Deep Embedded Clustering and Graph Neural Networks
di: Delzer, Luke, et al.
Pubblicazione: (2025)

High-Dimensional Analysis of Bootstrap Ensemble Classifiers
di: Tiomoko, Malik, et al.
Pubblicazione: (2025)

Preventing Model Collapse in Gaussian Process Latent Variable Models
di: Li, Ying, et al.
Pubblicazione: (2024)

Can Neural Networks Provide Latent Embeddings for Telemetry-Aware Greedy Routing?
di: Boltres, Andreas, et al.
Pubblicazione: (2026)

Novel Deep Neural Network Classifier Characterization Metrics with Applications to Dataless Evaluation
di: Dean, Nathaniel, et al.
Pubblicazione: (2024)

Deep Graph Neural Point Process For Learning Temporal Interactive Networks
di: Chen, Su, et al.
Pubblicazione: (2025)

Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers
di: Súkeník, Peter, et al.
Pubblicazione: (2025)

Understanding Representation of Deep Equilibrium Models from Neural Collapse Perspective
di: Sun, Haixiang, et al.
Pubblicazione: (2024)