Cover Image

Transformers Provably Learn Directed Acyclic Graphs via Kernel-Guided Mutual Information

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cheng, Yuan, Huang, Yu, Xiong, Zhe, Liang, Yingbin, Tan, Vincent Y. F.
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Information Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent
by: Yang, Tong, et al.
Published: (2025)

Information Gradient for Directed Acyclic Graphs: A Score-based Framework for End-to-End Mutual Information Maximization
by: Wadayama, Tadashi
Published: (2026)

In-Context Learning with Representations: Contextual Generalization of Trained Transformers
by: Yang, Tong, et al.
Published: (2024)

Fourier Analysis of Signals on Directed Acyclic Graphs (DAG) Using Graph Zero-Padding
by: Stankovic, Ljubisa, et al.
Published: (2023)

Structure Learning via Mutual Information
by: Nixon, Jeremy
Published: (2024)

Generalization in Federated Learning: A Conditional Mutual Information Framework
by: Wang, Ziqiao, et al.
Published: (2025)

Ensemble-Tight Second-Order Asymptotics and Exponents for Guessing-Based Decoding with Abandonment
by: Tan, Vincent Y. F., et al.
Published: (2025)

Preserving Core Structures of Social Networks via Information Guided Multi-Step Graph Pruning
by: Hu, Yutong, et al.
Published: (2025)

Provably Efficient Information-Directed Sampling Algorithms for Multi-Agent Reinforcement Learning
by: Zhang, Qiaosheng, et al.
Published: (2024)

Cross Mutual Information
by: Gohil, Chetan, et al.
Published: (2025)

Mutual Information Bounds in the Shuffle Model
by: Su, Pengcheng, et al.
Published: (2025)

MIMO Capacity Analysis and Channel Estimation for Electromagnetic Information Theory
by: Zhu, Jieao, et al.
Published: (2024)

Characterizing Dependence of Samples along the Langevin Dynamics and Algorithms via Contraction of $Φ$-Mutual Information
by: Liang, Jiaming, et al.
Published: (2024)

Vendi Information Gain: An Alternative To Mutual Information For Science And Machine Learning
by: Nguyen, Quan, et al.
Published: (2025)

Directivity Enhancement of Movable Antenna Arrays with Mutual Coupling
by: Xu, Wei, et al.
Published: (2026)

On Local Mutual-Information Privacy
by: Ngo, Khac-Hoang, et al.
Published: (2024)

The Mutual Information In The Vicinity of Capacity-Achieving Input Distributions
by: Nakiboğlu, Barış, et al.
Published: (2023)

Mutual Information Estimation via Normalizing Flows
by: Butakov, Ivan, et al.
Published: (2024)

Agentic Transformers Provably Learn to Search via Reinforcement Learning
by: Yang, Tong, et al.
Published: (2026)

Timely Best Arm Identification in Restless Shared Networks
by: Zhou, Mengqiu, et al.
Published: (2026)

Monitoring State Transitions in Markovian Systems with Sampling Cost
by: Saurav, Kumar, et al.
Published: (2025)

Indexed Minimum Empirical Divergence-Based Algorithms for Linear Bandits
by: Bian, Jie, et al.
Published: (2024)

$α$-Mutual Information for the Gaussian Noise Channel
by: Milanian, Mohammad, et al.
Published: (2026)

InfoNet: Neural Estimation of Mutual Information without Test-Time Optimization
by: Hu, Zhengyang, et al.
Published: (2024)

On the Exponential Convergence for Offline RLHF with Pairwise Comparisons
by: Chen, Zhirui, et al.
Published: (2024)

Nearest-Neighbours Estimators for Conditional Mutual Information
by: Witter, Jake, et al.
Published: (2024)

Memory Complexity of Estimating Entropy and Mutual Information
by: Berg, Tomer, et al.
Published: (2024)

Automatic Rank Determination for Low-Rank Adaptation via Submodular Function Maximization
by: Gao, Yihang, et al.
Published: (2025)

Mutual Information Estimation via Score-to-Fisher Bridge for Nonlinear Gaussian Noise Channels
by: Wadayama, Tadashi
Published: (2025)

Variable-Length Feedback Codes over Known and Unknown Channels with Non-vanishing Error Probabilities
by: Yavas, Recep Can, et al.
Published: (2024)

Mutual Information Multinomial Estimation
by: Chen, Yanzhi, et al.
Published: (2024)

Convexity of Mutual Information along the Fokker-Planck Flow
by: Zou, Jiayang, et al.
Published: (2025)

A Generalized Leakage Interpretation of Alpha-Mutual Information
by: Kamatsuka, Akira, et al.
Published: (2026)

$α$-leakage by Rényi Divergence and Sibson Mutual Information
by: Ding, Ni, et al.
Published: (2024)

Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot
by: Wang, Zixuan, et al.
Published: (2024)

Generative Learning Enhanced Intelligent Resource Management for Cell-Free Delay Deterministic Communications
by: Xiong, Shuangbo, et al.
Published: (2026)

Mutual Information Bounds for Lossy Common Information
by: de Andrade, Anderson
Published: (2025)

Provable Privacy Advantages of Decentralized Federated Learning via Distributed Optimization
by: Yu, Wenrui, et al.
Published: (2024)

Holographic Beamforming for Integrated Sensing and Communication with Mutual Coupling Effects
by: Zeng, Shuhao, et al.
Published: (2025)

A Mirror Descent-Based Algorithm for Corruption-Tolerant Distributed Gradient Descent
by: Wang, Shuche, et al.
Published: (2024)