Imagen de Portada

Transformers in Pseudo-Random Number Generation: A Dual Perspective on Theory and Practice

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Ran, Zeng, Lingshu
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

(How) Can Transformers Predict Pseudo-Random Numbers?
por: Tao, Tao, et al.
Publicado: (2025)

Rethinking Graph Out-Of-Distribution Generalization: A Learnable Random Walk Perspective
por: Sun, Henan, et al.
Publicado: (2025)

Generalizable Insights for Graph Transformers in Theory and Practice
por: Stoll, Timo, et al.
Publicado: (2025)

A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities
por: Dandi, Yatin, et al.
Publicado: (2024)

Transformers Are Born Biased: Structural Inductive Biases at Random Initialization and Their Practical Consequences
por: Li, Siquan, et al.
Publicado: (2026)

Toward General Digraph Contrastive Learning: A Dual Spatial Perspective
por: Su, Daohan, et al.
Publicado: (2025)

PQDT: Pseudo-Query Dual Transformer for Robust Point Cloud Restoration
por: Wu, Haoqing, et al.
Publicado: (2026)

SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators
por: Shafipour, Rasoul, et al.
Publicado: (2024)

On the Disconnect Between Theory and Practice of Neural Networks: Limits of the NTK Perspective
por: Wenger, Jonathan, et al.
Publicado: (2023)

A Random Matrix Theory Perspective on the Learning Dynamics of Multi-head Latent Attention
por: Jha, Nandan Kumar, et al.
Publicado: (2025)

A Practical Theory of Generalization in Selectivity Learning
por: Wu, Peizhi, et al.
Publicado: (2024)

Exploring Pseudo-Token Approaches in Transformer Neural Processes
por: Lara-Rangel, Jose, et al.
Publicado: (2025)

Randomness Helps Rigor: A Probabilistic Learning Rate Scheduler Bridging Theory and Deep Learning Practice
por: Devapriya, Dahlia, et al.
Publicado: (2024)

On the Trade-off between the Number of Nodes and the Number of Trees in a Random Forest
por: Akutsu, Tatsuya, et al.
Publicado: (2023)

Federated Unlearning Made Practical: Seamless Integration via Negated Pseudo-Gradients
por: Mora, Alessio, et al.
Publicado: (2025)

Prototype Training with Dual Pseudo-Inverse and Optimized Hidden Activations
por: Tucci, Mauro
Publicado: (2025)

Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory
por: Liu, Yexiang, et al.
Publicado: (2025)

Machine Learning Cryptanalysis of a Quantum Random Number Generator
por: Truong, Nhan Duy, et al.
Publicado: (2019)

Generalization and Membership Inference Attack a Practical Perspective
por: Rahmani, Fateme, et al.
Publicado: (2026)

Correction of Transformer-Based Models with Smoothing Pseudo-Projector
por: Bulgakov, Vitaly
Publicado: (2026)

Model Immunization from a Condition Number Perspective
por: Zheng, Amber Yijia, et al.
Publicado: (2025)

On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory
por: Chen, Guhan, et al.
Publicado: (2024)

Position Encoding with Random Float Sampling Enhances Length Generalization of Transformers
por: Shimizu, Atsushi, et al.
Publicado: (2026)

Using Common Random Numbers for Simulation-based Planning with Rollouts
por: Yadav, Sandarbh, et al.
Publicado: (2026)

LoRanPAC: Low-rank Random Features and Pre-trained Models for Bridging Theory and Practice in Continual Learning
por: Peng, Liangzu, et al.
Publicado: (2024)

A Confidence-Variance Theory for Pseudo-Label Selection in Semi-Supervised Learning
por: Liu, Jinshi, et al.
Publicado: (2026)

Agnostic Interactive Imitation Learning: New Theory and Practical Algorithms
por: Li, Yichen, et al.
Publicado: (2023)

Learning Randomized Algorithms with Transformers
por: von Oswald, Johannes, et al.
Publicado: (2024)

A Basin-Selection Perspective on Grokking via Singular Learning Theory
por: Cullen, Ben, et al.
Publicado: (2026)

Fourier Neural Operators Explained: A Practical Perspective
por: Duruisseaux, Valentin, et al.
Publicado: (2025)

Semi-supervised CAPP Transformer Learning via Pseudo-labeling
por: Gross, Dennis, et al.
Publicado: (2026)

In Transformer We Trust? A Perspective on Transformer Architecture Failure Modes
por: Mondal, Trishit, et al.
Publicado: (2026)

FastLogAD: Log Anomaly Detection with Mask-Guided Pseudo Anomaly Generation and Discrimination
por: Lin, Yifei, et al.
Publicado: (2024)

Expressivity of Transformers: A Tropical Geometry Perspective
por: Su, Ye, et al.
Publicado: (2026)

A Constrained Optimization Perspective of Unrolled Transformers
por: Porras-Valenzuela, Javier, et al.
Publicado: (2026)

Molecule Generation for Drug Design: a Graph Learning Perspective
por: Yang, Nianzu, et al.
Publicado: (2022)

Attention Sinks Are Provably Necessary in Softmax Transformers: Evidence from Trigger-Conditional Tasks
por: Ran-Milo, Yuval
Publicado: (2026)

Cooperative Pseudo Labeling for Unsupervised Federated Classification
por: Guo, Kuangpu, et al.
Publicado: (2025)

Spectraformer: A Unified Random Feature Framework for Transformer
por: Nguyen, Duke, et al.
Publicado: (2024)

An Approximation Theory Perspective on Machine Learning
por: Mhaskar, Hrushikesh N., et al.
Publicado: (2025)