Imagen de Portada

A Spectral Condition for Feature Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yang, Greg, Simon, James B., Bernstein, Jeremy
Formato:	Preprint
Publicado:	2023
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Modular Duality in Deep Learning
por: Bernstein, Jeremy, et al.
Publicado: (2024)

Spectral Conditioning of Attention Improves Transformer Performance
por: Saratchandran, Hemanth, et al.
Publicado: (2026)

Old Optimizer, New Norm: An Anthology
por: Bernstein, Jeremy, et al.
Publicado: (2024)

The Optimization Landscape of SGD Across the Feature Learning Strength
por: Atanasov, Alexander, et al.
Publicado: (2024)

SketchOGD: Memory-Efficient Continual Learning
por: Min, Youngjae, et al.
Publicado: (2023)

Extending $μ$P: Spectral Conditions for Feature Learning Across Optimizers
por: Gupta, Akshita, et al.
Publicado: (2026)

Outcome-Aware Spectral Feature Learning for Instrumental Variable Regression
por: Meunier, Dimitri, et al.
Publicado: (2025)

Demystifying Spectral Feature Learning for Instrumental Variable Regression
por: Meunier, Dimitri, et al.
Publicado: (2025)

A Spectral View of Adversarially Robust Features
por: Garg, Shivam, et al.
Publicado: (2018)

Spectrally Informed Learning of Fluid Flows
por: Shaffer, Benjamin D., et al.
Publicado: (2024)

Scalable Optimization in the Modular Norm
por: Large, Tim, et al.
Publicado: (2024)

Spectral Regularization for Diffusion Models
por: Chandran, Satish, et al.
Publicado: (2026)

Spectral Convolutional Conditional Neural Processes
por: Mohseni, Peiman, et al.
Publicado: (2024)

Spectral Self-supervised Feature Selection
por: Segal, Daniel, et al.
Publicado: (2024)

Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks
por: Kunin, Daniel, et al.
Publicado: (2025)

Global Convergence and Rich Feature Learning in $L$-Layer Infinite-Width Neural Networks under $μ$P Parametrization
por: Chen, Zixiang, et al.
Publicado: (2025)

On the Relationship Between Activation Outliers and Feature Death in Sparse Autoencoders
por: Simon, Elana, et al.
Publicado: (2026)

Statistical Significance of Feature Importance Rankings
por: Goldwasser, Jeremy, et al.
Publicado: (2024)

The Features at Convergence Theorem: a first-principles alternative to the Neural Feature Ansatz for how networks learn representations
por: Boix-Adsera, Enric, et al.
Publicado: (2025)

Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models
por: Karkada, Dhruva, et al.
Publicado: (2025)

SpectraKAN: Conditioning Spectral Operators
por: Cheng, Chun-Wun, et al.
Publicado: (2026)

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

Spectral Condition for $μ$P under Width-Depth Scaling
por: Zheng, Chenyu, et al.
Publicado: (2026)

Toward Scalable and Valid Conditional Independence Testing with Spectral Representations
por: Frohlich, Alek, et al.
Publicado: (2025)

Robust Multi-Modal Forecasting: Integrating Static and Dynamic Features
por: Qin, Jeremy
Publicado: (2025)

Graph Classification Gaussian Processes via Hodgelet Spectral Features
por: Alain, Mathieu, et al.
Publicado: (2024)

Training Transformers with Enforced Lipschitz Constants
por: Newhouse, Laker, et al.
Publicado: (2025)

Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning
por: Dandi, Yatin, et al.
Publicado: (2026)

A Matched Spectral Benchmark of Quantum Inspired Feature Maps
por: Ogunade, Toheeb, et al.
Publicado: (2026)

Spectral Superposition: A Theory of Feature Geometry
por: Ivanov, Georgi, et al.
Publicado: (2026)

Descriptor-Injected Cross-Modal Learning: A Systematic Exploration of Audio-MIDI Alignment via Spectral and Melodic Features
por: Méndez, Mariano Fernández
Publicado: (2026)

Review Non-convex Optimization Method for Machine Learning
por: Fotopoulos, Greg B, et al.
Publicado: (2024)

SpectralKrum: A Spectral-Geometric Defense Against Byzantine Attacks in Federated Learning
por: Tripathi, Aditya, et al.
Publicado: (2025)

Learning Expressive Random Feature Models via Parametrized Activations
por: Ma, Zailin, et al.
Publicado: (2024)

More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory
por: Simon, James B., et al.
Publicado: (2023)

Machine Learning based Analysis for Radiomics Features Robustness in Real-World Deployment Scenarios
por: Khan, Sarmad Ahmad, et al.
Publicado: (2025)

Learning Continually by Spectral Regularization
por: Lewandowski, Alex, et al.
Publicado: (2024)

Overcoming Data Limitations in Internet Traffic Forecasting: LSTM Models with Transfer Learning and Wavelet Augmentation
por: Saha, Sajal, et al.
Publicado: (2024)

Assessing Pre-Trained Models for Transfer Learning Through Distribution of Spectral Components
por: Zhang, Tengxue, et al.
Publicado: (2024)

Spectral-factorized Positive-definite Curvature Learning for NN Training
por: Lin, Wu, et al.
Publicado: (2025)