A Probabilistic Perspective on Model Collapse

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xu, Shirong, He, Hengzhi, Cheng, Guang
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Golden Ratio Weighting Prevents Model Collapse
di: He, Hengzhi, et al.
Pubblicazione: (2025)

Watermarking Generative Categorical Data
di: Gu, Bochao, et al.
Pubblicazione: (2024)

Utility Theory of Synthetic Data Generation
di: Xu, Shirong, et al.
Pubblicazione: (2023)

Let the Target Select for Itself: Data Selection via Target-Aligned Paths
di: Yang, Huitao, et al.
Pubblicazione: (2026)

Rate-Optimal Rank Aggregation with Private Pairwise Rankings
di: Xu, Shirong, et al.
Pubblicazione: (2024)

Discriminative Estimation of Total Variation Distance: A Fidelity Auditor for Generative Data
di: Tao, Lan, et al.
Pubblicazione: (2024)

Watermarking Generative Tabular Data
di: He, Hengzhi, et al.
Pubblicazione: (2024)

Breaking Distortion-free Watermarks in Large Language Models
di: Reynolds, Shayleen, et al.
Pubblicazione: (2025)

Probabilistic Uncertain Reward Model
di: Sun, Wangtao, et al.
Pubblicazione: (2025)

Do More Predictions Improve Statistical Inference? Filtered Prediction-Powered Inference
di: Xu, Shirong, et al.
Pubblicazione: (2026)

TimeAutoDiff: A Unified Framework for Generation, Imputation, Forecasting, and Time-Varying Metadata Conditioning of Heterogeneous Time Series Tabular Data
di: Suh, Namjoon, et al.
Pubblicazione: (2024)

When Less Is More: Binary Feedback Can Outperform Ordinal Comparisons in Ranking Recovery
di: Xu, Shirong, et al.
Pubblicazione: (2025)

A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective
di: Shi, Lianghe, et al.
Pubblicazione: (2025)

Preventing Model Collapse in Deep Canonical Correlation Analysis by Noise Regularization
di: He, Junlin, et al.
Pubblicazione: (2024)

Mixup Regularization: A Probabilistic Perspective
di: El-Laham, Yousef, et al.
Pubblicazione: (2025)

Understanding DNNs in Feature Interaction Models: A Dimensional Collapse Perspective
di: Wang, Jiancheng, et al.
Pubblicazione: (2026)

Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective
di: Xing, Yue, et al.
Pubblicazione: (2024)

Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements and Long-term Convergence
di: Yi, Bingji, et al.
Pubblicazione: (2025)

Cross Entropy versus Label Smoothing: A Neural Collapse Perspective
di: Guo, Li, et al.
Pubblicazione: (2024)

A Probabilistic Perspective on Unlearning and Alignment for Large Language Models
di: Scholten, Yan, et al.
Pubblicazione: (2024)

CTSyn: A Foundation Model for Cross Tabular Data Generation
di: Lin, Xiaofeng, et al.
Pubblicazione: (2024)

Scaling Tractable Probabilistic Circuits: A Systems Perspective
di: Liu, Anji, et al.
Pubblicazione: (2024)

Path-Dependent Denoising: A Non-Conservative Field Perspective on Order Collapse in Diffusion Language Models
di: Kim, Jeonseong
Pubblicazione: (2026)

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

A Theoretical Perspective: How to Prevent Model Collapse in Self-consuming Training Loops
di: Fu, Shi, et al.
Pubblicazione: (2025)

Strong Model Collapse
di: Dohmatob, Elvis, et al.
Pubblicazione: (2024)

Learning World Models With Hierarchical Temporal Abstractions: A Probabilistic Perspective
di: Shaj, Vaisakh
Pubblicazione: (2024)

Probabilistic Lipschitzness and the Stable Rank for Comparing Explanation Models
di: Simpson, Lachlan, et al.
Pubblicazione: (2024)

Optimal Watermark Generation under Type I and Type II Errors
di: He, Hengzhi, et al.
Pubblicazione: (2025)

Improve Fidelity and Utility of Synthetic Credit Card Transaction Time Series from Data-centric Perspective
di: Hsieh, Din-Yin, et al.
Pubblicazione: (2024)

Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation
di: He, Xixiang, et al.
Pubblicazione: (2026)

A Survey on Statistical Theory of Deep Learning: Approximation, Training Dynamics, and Generative Models
di: Suh, Namjoon, et al.
Pubblicazione: (2024)

Towards One Model for Classical Dimensionality Reduction: A Probabilistic Perspective on UMAP and t-SNE
di: Ravuri, Aditya, et al.
Pubblicazione: (2024)

Optimizer choice matters for the emergence of Neural Collapse
di: Zhao, Jim, et al.
Pubblicazione: (2026)

Layer Collapse in Diffusion Language Models
di: Conzelmann, Alexander, et al.
Pubblicazione: (2026)

Understanding Transformer from the Perspective of Associative Memory
di: Zhong, Shu, et al.
Pubblicazione: (2025)

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

On the Stability of Graph Convolutional Neural Networks: A Probabilistic Perspective
di: Zhang, Ning, et al.
Pubblicazione: (2025)

From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective
di: Chen, Tianhua
Pubblicazione: (2025)

Quantifying Error Propagation and Model Collapse in Diffusion Models
di: Khelifa, Nail B., et al.
Pubblicazione: (2026)