Random Feature Methods

Ask about this topic

Overview

Random feature methods replace expensive kernel computations or trained hidden layers with finite sets of randomized functions, making learning more scalable. Approaches include random Fourier and spectral features, structured projections, graph-based features, and adaptive or learned feature distributions, often paired with ridge regression or least-squares readouts. They are studied in kernel regression and classification, graph learning, PDE solving, time-series modeling, and attention, with theory covering approximation, learning rates, and robustness. A central challenge is balancing feature count and computational cost against accuracy and numerical conditioning, especially when data are misspecified or have exploitable structure.

Latest papers

CardsList

46 papers11 papers in the last four weeks, up 83% on the four weeks before. 0.1% of all new papers.

  1. Phase Transition from Random Features to Fully Trainable Networks

    Oct 22, 2026Xin He, Huan Lao, Xiliang Lu +1Neural Network Approximation TheoryPhase Transitions in Neural Networks

  2. Scalable and Adaptive Distribution Regression via Random Features

    Oct 17, 2026Yinsong Wang, Xiao Liu, Yu DingDistributional RegressionRandom Feature Methods

    School of Mechanical, Industrial and Material Engineering, University of Nevada Reno, Reno 89557, USA. · H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta 30332, USA.

  3. Adaptive Randomized Neural Networks for PDEs: Structure-Aware Feature Redistribution and Residual-Driven Block Enrichment

    Oct 15, 2026You Yang, Fei WangNeural PDE SolversRandom Feature Methods

    School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, Shaanxi 710049, China. · School of Mathematics and Statistics & State Key Laboratory of Multiphase Flow in Power Engineering, Xi’an Jiaotong University, Xi’an, Shaanxi 710049, China.

  4. Exact Scaling Laws for a Random-Features Bigram Model

    Oct 13, 2026Julian Enoch, Elvis DohmatobZipf's LawRandom Feature Methods

    Concordia University · Mila – Quebec AI Institute

  5. On the Optimality of Random Features under General Conditions: Misspecified Cases and Robust Learning

    Oct 13, 2026Caixing WangRandom Feature MethodsKernel Ridge Regression

    School of Statistics and Data Science, Southeast University, Nanjing, China

  6. Random Feature Pruning for Multi-Class Classification

    Oct 10, 2026Mohammad Amin Omidi, Babak Seyfe, Shahrokh ValaeeFeature SelectionRandom Feature Methods

    Information Theoretic Learning Systems Laboratory (ITLSL), Department of Electrical Engineering, Shahed University, Tehran, Iran · Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada

  7. Random Fourier Features in Near-Linear Time

    Oct 10, 2026Sepideh Mahabadi, Sandeep Silwal, Tal WagnerRandom Feature MethodsFourier Feature Embeddings

    Microsoft Research – Redmond · University of Wisconsin-Madison · Tel Aviv University

  8. Simulating Training Spikes of Deep Neural Networks by Layer-wise Random Feature Models

    Oct 9, 2026Ran Tian, Courtney PaquetteRandom Feature MethodsNeural Network Training Dynamics

    Google Deepmind

  9. The Expressive Power of Random-Feature MPNNs Across Graph Sizes

    Oct 8, 2026Robert R. Nerem, Mitchell Black, Antonis Vasileiou +2GNN ExpressivityMessage Passing Neural Networks

    University of California, San Diego · Rheinisch Westfälische Technische Hochschule Aachen

  10. Memorization and Malign Generalization in Conditional Diffusion Models with Random Features

    Oct 8, 2026Gwangho Kim, Sungyoon LeeRandom Feature MethodsConditional Diffusion Models

    Department of Computer Science Hanyang University, Seoul

  11. Quadratic Weak-to-Strong Generalization in Random Feature Networks via Random Matrix Theory

    Oct 6, 2026Deborah Oliveira, Elliot PaquetteWeak-to-Strong GeneralizationRandom Feature Methods

    McGill University Mila – Quebec AI Institute

  12. An Active-Bottleneck Mechanism for Weak-to-Strong Generalization

    Sep 27, 2026Mohammad Zeinalpour, Amir NajafiWeak-to-Strong GeneralizationRandom Feature Methods

    Department of Computer Engineering, Sharif University of Technology

  13. A Smoothed Discrepancy Principle for Random Feature Methods and Neural Networks

    Sep 17, 2026Mike Nguyen, Nicole MückeEarly StoppingNonparametric Regression

    Technical University of Braunschweig

  14. Online Supervised Dimension Reduction with Random Features: Diagnostics and Computational Trade-offs

    Sep 17, 2026Zhenlin Yao, Wei XiongPrincipal Component AnalysisRandom Feature Methods

    School of Statistics University of International Business and Economics Beijing, China

  15. Physics Informed Random Feature Neural Networks for Solving PDEs

    Sep 14, 2026Chi-An Chen, Chunyang Liao, Ming ZhongPDE SolvingRandom Feature Methods

    Department of Applied Mathematics, Mathematics, Illinois Institute of Technology, Chicago, IL, 60616 · Department of Mathematical Sciences, University of Arkansas, Fayetteville, AR, 72701 · Department of Mathematics, University of Houston, Houston, TX, 77204

  16. A Quantum-Inspired Dequantization Method for Diagonally Weighted Matrix Functions: Application to Learning with Optimized Random Features

    Sep 9, 2026Natsuto Isogai, Mio Murao, Hayata YamasakiQuantum-Inspired MLRandom Feature Methods

    Department of Physics, Graduate School of Science, The University of Tokyo, Tokyo, Japan · Department of Computer Science, Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan

  17. Spectral Convergence of Random Feature Method in Multiple Dimensions

    Sep 3, 2026Pingbing Ming, Hao YuPDE SolvingRandom Feature Methods

  18. Signed random Fourier features for fast density estimation with indefinite kernels

    Aug 29, 2026Xie Wang, Nicolas Langrené, Wen ChenKernel Density EstimationRandom Feature Methods

    Mathematical Institute, University of Oxford, Oxford, OX2 6GG, UK · Guangdong Provincial/Zhuhai Key Laboratory of Interdisciplinary Research and Application for Data Science, Beijing Normal-Hong Kong Baptist University, Zhuhai 519087, China.

  19. Adaptive Regularization for Random Features: A Neighboring Early-Stopping Rule with Oracle-Rate Guarantees

    Aug 26, 2026Caixing Wang, Zhibo Chen, Yue WangRandom Feature MethodsKernel Ridge Regression

    School of Statistics and Data Science, Southeast University · Faculty of Business for Science and Technology, School of Management, University of Science and Technology of China

  20. Uncertainty-Aware Ensemble Deep Randomized Neural Networks for Classification

    Aug 7, 2026M. Sajid, A. Quadir, A. Rahaman +2Ensemble LearningNeural Network Robustness

    Indian Institute of Technology Indore, Simrol, Indore, India · Qatar University, Qatar

  21. Random features for Grassmannian kernel approximation with bounded rank-one projections

    Aug 4, 2026Rémi Delogne, Laurent JacquesGeometric Representation LearningRandom Feature Methods

    INMA/ICTEAM, UCLouvain, Belgium

  22. A Coulomb Particle Model for Learning Kernel Attention in Transformers

    Jul 26, 2026Masoud Badiei Khuzani, Sharath Honnaiah, Atiq Islam +2Transformer AttentionEfficient Attention

    eBay Inc., San Jose, CA, USA

  23. A Structure-Adaptive Random Feature Method for High-Dimensional Elliptic PDEs

    Jul 22, 2026Jiale Linghu, Hao Dong, Yangshuai WangPDE SolvingRandom Feature Methods

    School of Mathematics and Statistics, Xidian University, Xi’an 710071, China. · Department of Mathematics, National University of Singapore, 10 Lower Kent Ridge Road, 119076, Singapore

  24. Accurate and Resource-Efficient Federated Continual Learning

    Jun 9, 2026Jebacyril Arockiaraj, Dhruv Parikh, Jayashree Adivarahan +2Communication-Efficient Distributed TrainingContinual Learning

    University of Southern California · Los Angeles, USA · DEVCOM Army Research Office +1

  25. Bernstein-Schur Kernels: Random Features by Sketched Modulation and Radial Randomization

    Jun 8, 2026Taha BouhsineFourier Feature EmbeddingsKernel Ridge Regression

    Azetta AI

  26. Generating Financial Time Series by Matching Random Convolutional Features

    Jun 3, 2026Konrad J. Mueller, Nikita Zozoulenko, Ben Wood +2Time Series GenerationRandom Feature Methods

    Imperial College London · JPMorgan Chase & Co.‡

  27. HalfNet: Randomized Neural Networks with Learned Subspace Geometry

    Jun 3, 2026Ethem AlpaydinNeural Representation GeometryRandom Feature Methods

    Independent Researcher Istanbul, Turkey

  28. On the Optimizer Dependence of Neural Scaling Laws

    May 28, 2026Vansh Ramani, Shourya Vir JainNatural Gradient MethodsNeural Network Optimization

    Department of Computer Science and Engineering, Indian Institute of Technology Delhi · Department of Electrical Engineering, Indian Institute of Technology Delhi

  29. Conditional KRR: Injecting Unpenalized Features into Kernel Methods with Applications to Kernel Thresholding

    May 25, 2026Rustem Takhanov, Zhenisbek AssylbekovKernel Ridge RegressionKernel Regression

    Department of Mathematics, Nazarbayev University, Astana, Kazakhstan · Nazarbayev University Research Administration, Astana, Kazakhstan · Purdue University Fort Wayne, Indiana, USA.

  30. Worse than Random: The Importance of a Baseline for Unsupervised Feature Selection

    May 21, 2026Muhammad Rajabinasab, Michael E. Houle, Oussama Chelly +1Unsupervised LearningRandom Feature Methods

    University of Southern Denmark, Odense, Denmark · New Jersey Institute of Technology, Newark, NJ, United States · oratio Technologies, Tunis, Tunisia