Imagen de Portada

A Two-Parameter Weibull Framework for Diagnosing Transformer Weight Distributions

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Ding, Tiexin
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Generalizing to New Dynamical Systems via Frequency Domain Adaptation
por: Qin, Tiexin, et al.
Publicado: (2025)

To Augment or Not to Augment? Diagnosing Distributional Symmetry Breaking
por: Lawrence, Hannah, et al.
Publicado: (2025)

Permutation Equivariant Neural Controlled Differential Equations for Dynamic Graph Representation Learning
por: Berndt, Torben, et al.
Publicado: (2025)

DFReg: A Physics-Inspired Framework for Global Weight Distribution Regularization in Neural Networks
por: Ruggieri, Giovanni
Publicado: (2025)

Scalable Weibull Graph Attention Autoencoder for Modeling Document Networks
por: Wang, Chaojie, et al.
Publicado: (2024)

Allocation of Parameters in Transformers
por: Yu, Ruoxi, et al.
Publicado: (2025)

Learning Dynamic Graph Embeddings with Neural Controlled Differential Equations
por: Qin, Tiexin, et al.
Publicado: (2023)

The Offline-Frontier Shift: Diagnosing Distributional Limits in Generative Multi-Objective Optimization
por: Holly, Stephanie, et al.
Publicado: (2026)

Parameter-Efficient Checkpoint Merging via Metrics-Weighted Averaging
por: Yu, Shi Jie, et al.
Publicado: (2025)

TFWT: Tabular Feature Weighting with Transformer
por: Zhang, Xinhao, et al.
Publicado: (2024)

Distributed Sign Momentum with Local Steps for Training Transformers
por: Yu, Shuhua, et al.
Publicado: (2024)

A network-constrain Weibull AFT model for biomarkers discovery
por: Angelini, Claudia, et al.
Publicado: (2024)

A Transformer-Based Approach for Diagnosing Fault Cases in Optical Fiber Amplifiers
por: Schneider, Dominic, et al.
Publicado: (2025)

Fast and Robust: Computationally Efficient Covariance Estimation for Sub-Weibull Vectors
por: He, Even
Publicado: (2025)

Transformer-based Parameter Estimation in Statistics
por: Yin, Xiaoxin, et al.
Publicado: (2024)

Adaptive Dual-Weighting Framework for Federated Learning via Out-of-Distribution Detection
por: Ling, Zhiwei, et al.
Publicado: (2026)

A Brain-to-Population Graph Learning Framework for Diagnosing Brain Disorders
por: Liao, Qianqian, et al.
Publicado: (2025)

Log Neural Controlled Differential Equations: The Lie Brackets Make a Difference
por: Walker, Benjamin, et al.
Publicado: (2024)

Preventing Data Leakage in EEG-Based Survival Prediction: A Two-Stage Embedding and Transformer Framework
por: Zhou, Yixin, et al.
Publicado: (2026)

A Unified Geometric Framework for Weighted Contrastive Learning
por: Vock, Raphael, et al.
Publicado: (2026)

Automated Immunophenotyping Assessment for Diagnosing Childhood Acute Leukemia using Set-Transformers
por: Lygizou, Elpiniki Maria, et al.
Publicado: (2024)

Towards Trustworthy Audio Deepfake Detection: A Systematic Framework for Diagnosing and Mitigating Gender Bias
por: Fursule, Aishwarya, et al.
Publicado: (2026)

Diagnosing Transformers: Illuminating Feature Spaces for Clinical Decision-Making
por: Hsu, Aliyah R., et al.
Publicado: (2023)

Weight Updates as Activation Shifts: A Principled Framework for Steering
por: Adila, Dyah, et al.
Publicado: (2026)

PEANuT: Parameter-Efficient Adaptation with Weight-aware Neural Tweakers
por: Zhong, Yibo, et al.
Publicado: (2024)

Equivalence of Context and Parameter Updates in Modern Transformer Blocks
por: Goldwaser, Adrian, et al.
Publicado: (2025)

Transformers Provably Learn Sparse XOR with Polylogarithmic Parameters
por: Han, Yaomengxi, et al.
Publicado: (2025)

Optimal Parameter and Neuron Pruning for Out-of-Distribution Detection
por: Chen, Chao, et al.
Publicado: (2024)

Learning to Weight Parameters for Training Data Attribution
por: Li, Shuangqi, et al.
Publicado: (2025)

Attention Saturation and Gradient Suppression at Inflection Layers: Diagnosing and Mitigating Bottlenecks in Transformer Adaptation
por: Zixian, Wang
Publicado: (2025)

Dynamic Weight Grafting: Localizing Finetuned Factual Knowledge in Transformers
por: Nief, Todd, et al.
Publicado: (2025)

Going Beyond the Edge: Distributed Inference of Transformer Models on Ultra-Low-Power Wireless Devices
por: Gräfe, Alexander, et al.
Publicado: (2026)

A Two-Timescale Approach for Wireless Federated Learning with Parameter Freezing and Power Control
por: Ouyang, Jinhao, et al.
Publicado: (2025)

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
por: Wang, Haiyang, et al.
Publicado: (2024)

Aggregation Models with Optimal Weights for Distributed Gaussian Processes
por: Chen, Haoyuan, et al.
Publicado: (2024)

LoGAH: Predicting 774-Million-Parameter Transformers using Graph HyperNetworks with 1/100 Parameters
por: Zhou, Xinyu, et al.
Publicado: (2024)

Exact Conversion of In-Context Learning to Model Weights in Linearized-Attention Transformers
por: Chen, Brian K, et al.
Publicado: (2024)

In-Context Algorithm Emulation in Fixed-Weight Transformers
por: Hu, Jerry Yao-Chieh, et al.
Publicado: (2025)

Understanding and Exploiting Weight Update Sparsity for Communication-Efficient Distributed RL
por: Miahi, Erfan, et al.
Publicado: (2026)

Deep Out-of-Distribution Uncertainty Quantification via Weight Entropy Maximization
por: de Mathelin, Antoine, et al.
Publicado: (2023)