Imagen de Portada

Golden Ratio Weighting Prevents Model Collapse

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	He, Hengzhi, Xu, Shirong, Cheng, Guang
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

A Probabilistic Perspective on Model Collapse
por: Xu, Shirong, et al.
Publicado: (2025)

Watermarking Generative Categorical Data
por: Gu, Bochao, et al.
Publicado: (2024)

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

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

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

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

Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapse
por: Alman, Josh, et al.
Publicado: (2025)

Preventing Model Collapse Under Overparametrization: Optimal Mixing Ratios for Interpolation Learning and Ridge Regression
por: Garg, Anvit, et al.
Publicado: (2025)

Golden Ratio-Based Sufficient Dimension Reduction
por: Yang, Wenjing, et al.
Publicado: (2024)

Watermarking Generative Tabular Data
por: He, Hengzhi, et al.
Publicado: (2024)

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

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

Explaining and Preventing Alignment Collapse in Iterative RLHF
por: Gauthier, Etienne, et al.
Publicado: (2026)

Preventing Dimensional Collapse in Self-Supervised Learning via Orthogonality Regularization
por: He, Junlin, et al.
Publicado: (2024)

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

Preventing Model Collapse via Contraction-Conditioned Neural Filters
por: Han, Zongjian, et al.
Publicado: (2025)

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

Understanding and Preventing Entropy Collapse in RLVR with On-Policy Entropy Flow Optimization
por: Xu, Huimin, et al.
Publicado: (2026)

Feature Normalization Prevents Collapse of Non-contrastive Learning Dynamics
por: Bao, Han
Publicado: (2023)

Preventing Representational Rank Collapse in MPNNs by Splitting the Computational Graph
por: Roth, Andreas, et al.
Publicado: (2024)

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

Sequential Subspace Noise Injection Prevents Accuracy Collapse in Certified Unlearning
por: Dolgova, Polina, et al.
Publicado: (2026)

Preventing Collapse in Contrastive Learning with Orthonormal Prototypes (CLOP)
por: Li, Huanran, et al.
Publicado: (2024)

Preventing Curriculum Collapse in Self-Evolving Reasoning Systems
por: Mishra, Vaibhav
Publicado: (2026)

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

Hard Regularization to Prevent Deep Online Clustering Collapse without Data Augmentation
por: Mahon, Louis, et al.
Publicado: (2023)

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

TQL: Scaling Q-Functions with Transformers by Preventing Attention Collapse
por: Dong, Perry, et al.
Publicado: (2026)

Anchored Alignment: Preventing Positional Collapse in Multimodal Recommender Systems
por: Jeong, Yonghun, et al.
Publicado: (2026)

Why Prototypes Collapse: Diagnosing and Preventing Partial Collapse in Prototypical Self-Supervised Learning
por: Arteaga, Gabriel Y., et al.
Publicado: (2025)

Towards Understanding Neural Collapse: The Effects of Batch Normalization and Weight Decay
por: Pan, Leyan, et al.
Publicado: (2023)

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

CURE: Critical-Token-Guided Re-Concatenation for Entropy-Collapse Prevention
por: Li, Qingbin, et al.
Publicado: (2025)

Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning
por: Arefin, Md Rifat, et al.
Publicado: (2024)

Strong Model Collapse
por: Dohmatob, Elvis, et al.
Publicado: (2024)

Golden Ratio Search: A Low-Power Adversarial Attack for Deep Learning based Modulation Classification
por: Sadhukhan, Deepsayan, et al.
Publicado: (2024)

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

Golden Noise for Diffusion Models: A Learning Framework
por: Zhou, Zikai, et al.
Publicado: (2024)

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

LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning
por: Kang, Haoqiang, et al.
Publicado: (2026)