Copertina

Three Mechanisms of Feature Learning in a Linear Network

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xu, Yizhou, Ziyin, Liu
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Remove Symmetries to Control Model Expressivity and Improve Optimization
di: Ziyin, Liu, et al.
Pubblicazione: (2024)

Parameter Symmetry Potentially Unifies Deep Learning Theory
di: Ziyin, Liu, et al.
Pubblicazione: (2025)

Noise Balance and Stationary Distribution of Stochastic Gradient Descent
di: Ziyin, Liu, et al.
Pubblicazione: (2023)

When Does Learning Renormalize? Sufficient Conditions for Power Law Spectral Dynamics
di: Zhang, Yizhou
Pubblicazione: (2025)

Finite Sample Analysis of Linear Temporal Difference Learning with Arbitrary Features
di: Xie, Zixuan, et al.
Pubblicazione: (2025)

Enhancing Imbalanced Node Classification via Curriculum-Guided Feature Learning and Three-Stage Attention Network
di: Fofanah, Abdul Joseph, et al.
Pubblicazione: (2026)

Learning Hierarchical Polynomials of Multiple Nonlinear Features with Three-Layer Networks
di: Fu, Hengyu, et al.
Pubblicazione: (2024)

The Weight Gram Matrix Captures Sequential Feature Linearization in Deep Networks
di: Cha, Taehun, et al.
Pubblicazione: (2026)

Compositional Generalization via Forced Rendering of Disentangled Latents
di: Liang, Qiyao, et al.
Pubblicazione: (2025)

Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
di: Defilippis, Leonardo, et al.
Pubblicazione: (2025)

Universal One-third Time Scaling in Learning Peaked Distributions
di: Liu, Yizhou, et al.
Pubblicazione: (2026)

Almost Sure Convergence of Linear Temporal Difference Learning with Arbitrary Features
di: Wang, Jiuqi, et al.
Pubblicazione: (2024)

Understanding the Emergence of Multimodal Representation Alignment
di: Tjandrasuwita, Megan, et al.
Pubblicazione: (2025)

Self-cross Feature based Spiking Neural Networks for Efficient Few-shot Learning
di: Xu, Qi, et al.
Pubblicazione: (2025)

Feature contamination: Neural networks learn uncorrelated features and fail to generalize
di: Zhang, Tianren, et al.
Pubblicazione: (2024)

Shortcut Features as Top Eigenfunctions of NTK: A Linear Neural Network Case and More
di: Lim, Jinwoo, et al.
Pubblicazione: (2026)

Hamiltonian Mechanics of Feature Learning: Bottleneck Structure in Leaky ResNets
di: Jacot, Arthur, et al.
Pubblicazione: (2024)

Three Pathways to Neurosymbolic Reinforcement Learning with Interpretable Model and Policy Networks
di: Graf, Peter, et al.
Pubblicazione: (2024)

Learning Distinguishable Representations in Deep Q-Networks for Linear Transfer
di: Sathish, Sooraj, et al.
Pubblicazione: (2025)

Feature Repulsion and Spectral Lock-in: An Empirical Study of Two-Layer Network Grokking
di: Xu, Yongzhong
Pubblicazione: (2026)

TANGNN: a Concise, Scalable and Effective Graph Neural Networks with Top-m Attention Mechanism for Graph Representation Learning
di: E, Jiawei, et al.
Pubblicazione: (2024)

Learning Probabilities of Causation with Mask-Augmented Data
di: Wang, Shuai, et al.
Pubblicazione: (2025)

Thermodynamic Irreversibility of Training Algorithms
di: Ziyin, Liu, et al.
Pubblicazione: (2026)

On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD
di: Zhang, Tongcheng, et al.
Pubblicazione: (2026)

Robust Offline Reinforcement Learning with Linearly Structured f-Divergence Regularization
di: Tang, Cheng, et al.
Pubblicazione: (2024)

Identifying General Mechanism Shifts in Linear Causal Representations
di: Chen, Tianyu, et al.
Pubblicazione: (2024)

Data Curation Through the Lens of Spectral Dynamics: Static Limits, Dynamic Acceleration, and Practical Oracles
di: Zhang, Yizhou, et al.
Pubblicazione: (2025)

Operator Feature Neural Network for Symbolic Regression
di: Deng, Yusong, et al.
Pubblicazione: (2024)

Solving Deep Reinforcement Learning Tasks with Evolution Strategies and Linear Policy Networks
di: Wong, Annie, et al.
Pubblicazione: (2024)

Provable Effects of Data Replay in Continual Learning: A Feature Learning Perspective
di: Ding, Meng, et al.
Pubblicazione: (2026)

Contextual Linear Bandits under Noisy Features: Towards Bayesian Oracles
di: Kim, Jung-hun, et al.
Pubblicazione: (2017)

Three Dogmas of Reinforcement Learning
di: Abel, David, et al.
Pubblicazione: (2024)

TinyGraph: Joint Feature and Node Condensation for Graph Neural Networks
di: Liu, Yezi, et al.
Pubblicazione: (2024)

Feature Learning Dynamics in Infinite-Depth Neural Networks
di: Yao, Zihan, et al.
Pubblicazione: (2025)

Feature Shift Localization Network
di: Barrabés, Míriam, et al.
Pubblicazione: (2025)

Causal Feature Selection for Responsible Machine Learning
di: Moraffah, Raha, et al.
Pubblicazione: (2024)

Lecture Notes on Linear Neural Networks: A Tale of Optimization and Generalization in Deep Learning
di: Cohen, Nadav, et al.
Pubblicazione: (2024)

Unveiling the Power of Sparse Neural Networks for Feature Selection
di: Atashgahi, Zahra, et al.
Pubblicazione: (2024)

Transform then Explore: a Simple and Effective Technique for Exploratory Combinatorial Optimization with Reinforcement Learning
di: Pu, Tianle, et al.
Pubblicazione: (2024)

Exploiting Latent Linearity in LLMs Improves Explainable Molecular Representation Learning
di: Li, Zhuoran, et al.
Pubblicazione: (2024)