Cover Image

The Features at Convergence Theorem: a first-principles alternative to the Neural Feature Ansatz for how networks learn representations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Boix-Adsera, Enric, Mallinar, Neil, Simon, James B., Belkin, Mikhail
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Secret mixtures of experts inside your LLM
by: Boix-Adsera, Enric
Published: (2025)

On the inductive bias of infinite-depth ResNets and the bottleneck rank
by: Boix-Adsera, Enric
Published: (2025)

Toward universal steering and monitoring of AI models
by: Beaglehole, Daniel, et al.
Published: (2025)

Towards a theory of model distillation
by: Boix-Adsera, Enric
Published: (2024)

The power of fine-grained experts: Granularity boosts expressivity in Mixture of Experts
by: Boix-Adsera, Enric, et al.
Published: (2025)

Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting
by: Mallinar, Neil, et al.
Published: (2022)

Breaking Data Symmetry is Needed For Generalization in Feature Learning Kernels
by: Bernal, Marcel Tomàs, et al.
Published: (2026)

Let Me Think! A Long Chain-of-Thought Can Be Worth Exponentially Many Short Ones
by: Mirtaheri, Parsa, et al.
Published: (2025)

When can transformers reason with abstract symbols?
by: Boix-Adsera, Enric, et al.
Published: (2023)

The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of sparse functions on two-layer neural networks
by: Abbe, Emmanuel, et al.
Published: (2022)

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

A Gap Between the Gaussian RKHS and Neural Networks: An Infinite-Center Asymptotic Analysis
by: Kumar, Akash, et al.
Published: (2025)

Impossibility Theorems for Feature Attribution
by: Bilodeau, Blair, et al.
Published: (2022)

Convergent Evolution: How Different Language Models Learn Similar Number Representations
by: Fu, Deqing, et al.
Published: (2026)

Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probing
by: Mirtaheri, Parsa, et al.
Published: (2026)

General and Efficient Steering of Unconditional Diffusion
by: Wang, Qingsong, et al.
Published: (2026)

Feature learning as alignment: a structural property of gradient descent in non-linear neural networks
by: Beaglehole, Daniel, et al.
Published: (2024)

Comparative Analysis of QNN Architectures for Wind Power Prediction: Feature Maps and Ansatz Configurations
by: Hangun, Batuhan, et al.
Published: (2025)

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

Emergence in non-neural models: grokking modular arithmetic via average gradient outer product
by: Mallinar, Neil, et al.
Published: (2024)

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

Addressing divergent representations from causal interventions on neural networks
by: Grant, Satchel, et al.
Published: (2025)

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

Explicit Feature Interaction-aware Graph Neural Networks
by: Kim, Minkyu, et al.
Published: (2022)

InterPLM: Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders
by: Simon, Elana, et al.
Published: (2024)

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

Training-free Graph Neural Networks and the Power of Labels as Features
by: Sato, Ryoma
Published: (2024)

Graph Neural Networks with Feature and Structure Aware Random Walk
by: Zhuo, Wei, et al.
Published: (2021)

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

Mitigating Overfitting in Graph Neural Networks via Feature and Hyperplane Perturbation
by: Choi, Yoonhyuk, et al.
Published: (2022)

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

A Stable Neural Statistical Dependence Estimator for Autoencoder Feature Analysis
by: Hu, Bo, et al.
Published: (2026)

TangledFeatures: Robust Feature Selection in Highly Correlated Spaces
by: Sunny, Allen Daniel
Published: (2025)

Augmenting learning in neuro-embodied systems through neurobiological first principles
by: Rodriguez-Garcia, Alejandro, et al.
Published: (2024)

Eigenvectors of the De Bruijn Graph Laplacian: A Natural Basis for the Cut and Cycle Space
by: Philippakis, Anthony, et al.
Published: (2024)

Curriculum reinforcement learning with measurable task representation learning
by: Wen, Yongyan, et al.
Published: (2026)

Multi-View Graph Feature Propagation for Privacy Preservation and Feature Sparsity
by: Harari, Etzion, et al.
Published: (2025)

Meta-learning how to Share Credit among Macro-Actions
by: Hosu, Ionel-Alexandru, et al.
Published: (2025)

Decoding complexity: how machine learning is redefining scientific discovery
by: Vinuesa, Ricardo, et al.
Published: (2024)

The Impact of Feature Embedding Placement in the Ansatz of a Quantum Kernel in QSVMs
by: Salmenperä, Ilmo, et al.
Published: (2024)