Feature Learning

Follow this topic Ask about this topic

Recent momentum

-75%

3 papers in the last 28 days · 0.1% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-14

1 new paper

A weekly snapshot of new work published in Feature Learning.

Period ending 2026-09-07

2 new papers

A weekly snapshot of new work published in Feature Learning.

84 papers

Latest in Feature Learning

Open your feed →

Structured Features Overfit Where Random Features Grok
Sep 14, 2026Chon-Fai Kam, Miloud Bessafi, Frederic CadetOver-Parameterized Neural Networks Feature Learning
Where Decoder Cosine Similarity Fails for SAE Feature Flow Discovery
Sep 14, 2026Hendrik Droste, Christian Medeiros Adriano, Kathrin Korte +1Transformer Residual Streams Feature Learning
A Dominant Diffuse Phase in the Sparse Autoencoder Phase Diagram
Sep 9, 2026Alexis D. PlascenciaSparse Autoencoders Feature Learning
GIFT: Guided Intermediate Feature Training via Action-Oriented Structural Supervision for Robotic Manipulation
Sep 3, 2026Yupeng Zheng, Xiang Li, Songen Gu +11Robotic Manipulation Vision-Language-Action
Revenge of Monosemanticity: Neuron Specialization as a New Form of Feature Learning in MLPs
Aug 25, 2026Amirhesam Abedsoltan, Enric Boix-Adsera, Fivos Kalogiannis +1Feature Learning Multilayer Perceptrons
Accelerated Learning of High Dimensional Functions with a Tensor-Featured Training Network
Aug 11, 2026Karl Pierce, Yuehaw Khoo, Haizhao YangLow-Rank Tensor Decomposition High-Dimensional
Black-Box Knowledge Transfer across Distinct Feature Sets
Aug 10, 2026Oh-Ran Kwon, Daeyoung HamTransferable Knowledge Feature Learning
A Controlled Study of Feature-Based Knowledge Distillation Across Student Designs
Aug 8, 2026Abhinand Balachandran, Praveen PrashantHeterogeneous Knowledge Distillation Feature Learning
Hidden Gauge Controls Feature Specialization in ReLU Networks
Aug 7, 2026Tongxi WangFeature Learning Structured Pruning
Cascading Through the Hierarchy: Regularizer-Induced Feature Detection as Phase Transitions in Deep Linear Neural Networks
Aug 6, 2026Björn Ladewig, Ibrahim Talha Ersoy, Karoline WiesnerFeature Learning Phase Transitions
BRiG-AFA: Bellman Risk-to-Go Learning for Non-Myopic Active Feature Acquisition
Aug 3, 2026Jiaorong Feng, Qian Li, Ying LiActive Learning Feature Learning
Kohn-Sham Spectral Embedding on Sparse Graphs at the Nishimori Temperature for Image Classification
Jul 30, 2026V. S. Usatyuk, D. A. Sapozhnikov, S. I. EgorovFeature Learning Convolutional Neural Networks
DAS-PMVC: A Framework for Partial Multi-View Clustering via Dual Alignment and Structure Enhancement
Jul 30, 2026Shubin Ma, Liang Zhao, Chuanye He +4Multi-View Multimodal Alignment
Toward Multi-Modal Deep Learning for Pulmonary Disease Classification: A Texture-Based Machine Learning Pilot Study on Public Chest X-Ray Data
Jul 29, 2026Yogisri Pujitha ChinthotiChest X-Ray Multimodal Deep Learning
Bit-Accurate FPGA Evaluation of Learned Feature Gating in a Fixed-Point Fourier-Feature Automatic Modulation Classifier
Jul 27, 2026Gawthaman Senthilvelan, Luthira AbeykoonAutomatic Modulation Classification Field-Programmable Gate Arrays
A Coulomb Particle Model for Learning Kernel Attention in Transformers
Jul 26, 2026Masoud Badiei Khuzani, Sharath Honnaiah, Atiq Islam +2Feature Learning Transformer Attention
Causal dictionary learning reveals and validates transcription-factor binding features in genomic language models
Jul 21, 2026Sarwan AliTranscriptomics Learnable Probe Vectors
SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignment
Jul 16, 2026Saad Ejaz, Miguel Fernandez-Cortizas, Javier Civera +2Geometric Machine Learning Feature Learning
Fourier Preconditioning for Neural Feature Learning
Jul 2, 2026Preston Pitzer, Anish Pradhan, Harpreet S. DhillonFeature Learning Fourier
K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks
Jul 1, 2026Gil PasternakFeature Learning Machine Learning
SGD Provably Prioritizes a Shortcut Spurious Feature in the XOR Model
Jun 29, 2026Tyler LaBonte, Vidya MuthukumarFeature Learning Rectified Linear Unit Networks
From Spatial to Spectral: An Efficient, Frequency-Guided Feature Representation Learner for Small Object Detection
Jun 22, 2026Yuhan Rui, Shihan Qiao, Yibin Lou +7Feature Pyramid Networks Spatio-Temporal Fusion
Effective Dimension Governs Generalization in Quantum Kernel Vision Models
Jun 18, 2026Jian Xu, Delu Zeng, John Paisley +1Quantum Kernels Entanglement
Private Learning with Public Feature Conditioning
Jun 17, 2026Shuli Jiang, Walid Krichene, Nicolas MayorazDifferential Privacy Dp-Sgd
Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders
Jun 10, 2026Gleb Gerasimov, Timofei Rusalev, Nikita Balagansky +3Sparse Autoencoders Feature Learning
Muon Learns More Robust and Transferable Features than Adam
Jun 8, 2026Tianyu Ruan, Fengzhuo Zhang, Shuche Wang +1Adam Muon
Interactions Between Crosscoder Features: A Compact Proofs Perspective
Jun 8, 2026Dmitry Manning-Coe, Thomas Read, Anna Soligo +4Sparse Autoencoders Learnable Probe Vectors
Low-Frequency Shortcuts in Texture-Driven Visual Learning
Jun 2, 2026Utku Şirin, Cathy Hou, David Alvarez-Melis +1Low Frequency Luminance Feature Learning
Unlocking Feature Learning in Gated Delta Networks at Scale
Jun 2, 2026Yifeng Liu, Quanquan GuLearning Rates Hyperparameter
What Do Students Learn? A Feature-Level Analysis of Dark Knowledge
Jun 2, 2026Seungu Kang, Songkuk KimHeterogeneous Knowledge Distillation Feature Learning
Query Lens: Interpreting Sparse Key-Value Features with Indirect Effects
May 30, 2026Hwiyeong Lee, Ingyu Bang, Uiji Hwang +2Improving Sparse Autoencoders Sparse Autoencoders
On the Relationship Between Activation Outliers and Feature Death in Sparse Autoencoders
May 29, 2026Elana Simon, Etowah Adams, James ZouSparse Autoencoders Model Activations
Interpreting FCDNNs via RG on Exponential Family
May 29, 2026Fuzhou Gong, Zigeng XiaRenormalization Group Deep Neural Network
Eigen-Spike Emergence and Quadratic Equivalents for Conjugate Kernels on Nonlinearly Separable Data
May 28, 2026Collin Cranston, Zhichao Wang, Todd Kemp +1Largest Eigenvalue Neural Tangent Kernel
ST-ColoNet: Spatio-Temporal Colon Segment Recognition via Hybrid Attention and Edge-Guided Feature Learning
May 27, 2026Crystal Cai, Ziyi Wang, Zhengjie Zhang +3Colonoscopy State-Of-The-Art Unsupervised Class-Aware Image Segmentation Methods
Feature Learning in Wide Neural Networks under $μ$ P: Identifiability and Sparse-Dictionary Decomposition of the Mean-Field LimitFeature Learning in Wide Neural Networks under μP: Identifiability and Sparse-Dictionary Decomposition of the Mean-Field Limit
May 23, 2026Akmal XodarevTwo-Layer Neural Networks Feature Learning
A Matched Spectral Benchmark of Quantum Inspired Feature Maps
May 23, 2026Toheeb Ogunade, Taofeek Kassim, Etinosa OsaroQuantum Quantum Error Correction
Feature Lottery? A Bifurcation Theory of Concept Emergence
May 22, 2026Fuming YangFeature Learning Bifurcation
The Implicit Bias of Depth: From Neural Collapse to Softmax Codes
May 21, 2026Connall Garrod, Jonathan P. Keating, Christos ThrampoulidisNeural Collapse Feature Learning
Gaussian Sheaf Neural Networks
May 20, 2026André Ribeiro, Ana Luiza Tenório, Tiago da Silva +1Graph Neural Networks Graph Learning
BCI-sift: An automated feature selection toolbox for Brain Computer Interface applications
May 19, 2026Elena C Offenberg, Dirk Keller, Mariska J Vansteensel +3Brain-Computer Interface Feature Selection
Implicit Bias of Mirror Flow in Homogeneous Neural Networks: Sparse and Dense Feature Learning
May 19, 2026Tom Jacobs, Guido MontufarFeature Learning Utility Maximization
Aligned Training: A Parameter-Free Method to Improve Feature Quality and Stability of Sparse Autoencoders (SAE)
May 18, 2026Michał Brzozowski, Neo Christopher ChungSparse Autoencoders Feature Learning
Pointwise Generalization in Deep Neural Networks
May 18, 2026Shaojie Li, Yunbei XuGeneralization Bounds Deep Neural Network
VISAFF: Speaker-Centered Visual Affective Feature Learning for Emotion Recognition in Conversation
May 18, 2026Linan ZHU, Zihao Zhai, Xiao Han +4Speech Emotion Recognition Emotion Recognition
Canonical Regularisation of Wide Feature-Learning Neural Networks
May 18, 2026George Whittle, Pranav Vaidhyanathan, Juliusz Ziomek +2Feature Learning Regularization Methods
Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent
May 18, 2026Behrad Moniri, Hamed HassaniTwo-Layer Neural Networks Feature Learning
How does feature learning reshape the function space?
May 18, 2026João Lobo, Bruno Loureiro, Long Tran-Than +1Feature Learning Two-Layer Neural Networks
A Fourier perspective on the learning dynamics of neural networks: from sample complexities to mechanistic insights
May 16, 2026Fabiola Ricci, Claudia Merger, Sebastian GoldtFeature Learning Fourier
From Weight Perturbation to Feature Attribution for Explaining Fully Connected Neural Networks
May 14, 2026Thodoris Lymperopoulos, Denia KanellopoulouFeature Attribution Feature Learning
GQA-μP: The maximal parameterization update for grouped query attention
May 14, 2026Kyle R. Chickering, Huijuan Wang, Mengxi Wu +7Model Weights Hyperparameter
Learning with Shallow Neural Networks on Cluster-Structured Features
May 14, 2026Elisabetta Cornacchia, Laurent MassouliéLow-Dimensional Structure Two-Layer Neural Networks
Scaling Laws from Sequential Feature Recovery: A Solvable Hierarchical Model
May 14, 2026Arie Wortsman-Zurich, Hugo Tabanelli, Yatin Dandi +2Feature Learning Scaling Laws
Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning
May 13, 2026Yatin Dandi, Matteo Vilucchio, Luca Arnaboldi +2Feature Learning Two-Layer Neural Networks
The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge
May 13, 2026Ryoya Awano, Taiji SuzukiFeature Learning Stochastic Gradient Descent
AGOP as Explanation: From Feature Learning to Per-Sample Attribution in Image Classifiers
May 12, 2026Raj Kiran Gupta KatakamFeature Attribution Gradcam
Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks
May 11, 2026Minh-Toan Nguyen, Jean BarbierFeature Learning Scaling Laws
Characterizing the Generalization Error of Random Feature Regression with Arbitrary Data-Augmentation
May 11, 2026Lucas Morisset, Alain Durmus, Adrien HardyRegression Regularization Methods
Scalable Gaussian process inference via neural feature maps
May 11, 2026Anthony StephensonGaussian Process Feature Learning
The Geometric Structure of Models Learning Sparse Data
May 8, 2026Thomas Walker, T. Mitchell Roddenberry, Ahmed Imtiaz Humayun +2Feature Learning Geometric Reasoning

Sep 14, 2026 · cs.LGJ/K move · Enter open · S save

Structured Features Overfit Where Random Features Grok

Chon-Fai Kam, Miloud Bessafi, Frederic Cadet

Xu, Vardi and Safran (ICML 2026) prove that over-parameterized ridge regression over an unstructured random Gaussian feature map groks, with the delay between memorization and generalization growing as

1/λ

in the weight decay. We show that on a structured feature map the same delay does not appear. For a band-limited Fourier feature map over

\mathbb{Z}_p^2

carrying a single-character target that lies inside the expressible class, enlarging the band at fixed positive weight decay drives peak held-out accuracy monotonically from

1.00

0.07

, with no memorize-then-generalize regime anywhere along the sweep. The degradation is not an interpolation effect. It sets in at capacity ratio

q/n = 0.638

, far below the interpolation threshold, on separate grounds from the exact null space that appears above it. What does have a sharp boundary is the active support. Holding the nominal dimension fixed and masking the band back to

1089

active modes restores held-out accuracy of

1.000

with zero variance across seeds, while the full

4225

-mode band collapses to

0.185

. The number of active modes acts through the teacher-weighted spectrum of the empirical Gram matrix and not through the capacity ratio, which makes this a statement about feature geometry and not a restatement of double descent.

Over-Parameterized Neural Networks Feature Learning Kernel Ridge Regression

Open paper Ask about it PDF