PySVM : A NumPy implementation of SVM based on SMO algorithm. Numpy构建SVM分类、回归与单分类，支持缓存机制与随机傅里叶特征

Johnson-Lindenstrauss transform (JLT), random projections (RP), fast Johnson-Lindenstrauss transform (FJLT), and randomized Hadamard transform (RHT) in python 3.x

GRB triangulation via non-stationary time-series models

Efficient approximate Bayesian machine learning

A time-delayed light curve simulation code for GRB location triangulation via random Fourier features.

Incremental Sparse Spectrum Gaussian Process Regression

Official implementation of PromptSplit: kernel-based framework to detect prompt-level disagreements in generative models (text-to-image, LLMs). Identifies divergent prompt clusters via tensor embeddings & random projections for scalability.

We present anomaly detection model that combines the strong statistical foundation of density-estimation-based anomaly detection methods with the representation-learning ability of deep-learning models. The method combines an autoencoder, for learning a low-dimensional representation of the data, with a density-estimation model based on RFF

The official implementation of Randomly Weighted Feature Network for Visual Relationship Detection Tasks (CLeaR@AAAI2022)

[AISTATS 2023] Error Estimation for Random Fourier Features

[Pattern Recognition 2023] End-to-end Kernel Learning via Generative Random Fourier Features

Kernel Density Estimation (KDE) is a powerful non-parametric method to estimate continuous probability density functions from data. However, traditional KDE scales poorly with dataset size since it requires the full dataset at prediction time. This repository provides a computationally efficient alternative that approximates KDE with RFF

Python implementation of the paper Random Fourier Features based SLAM (https://arxiv.org/pdf/2011.00594.pdf)

The official implementation of Randomly Weighted Feature Network for Visual Relationship Detection Tasks (CLeaR@AAAI2022)

Bayesian inference using sparse gaussian processes from tinygp. Examples include 1D and 2D implementation.

Advanced Image Enhancement and Data Recovery: Superresolution Techniques and Missing Data Handling

Eigenvalues & AI, Quantum Physics, Emergence — interactive math blog with React visualizations, KRR Chat demo, and KaTeX. DE+EN at ki-mathias.de

A language model with no neural network — just eigenvalues, kernel ridge regression, and 120 lines of JavaScript. Runs in your browser. Color-coded memorization vs. generalization.

LINMA2472: Algorithms in Data Science

Empirical study of linear, exact-kernel, and approximate-kernel classifiers on nonlinear binary classification tasks.