An implementation of the Nyströmformer, using Nystrom method to approximate standard self attention
Vision Xformers
Enitor provides the MATLAB implementation of several large-scale kernel methods.
Python implementation of RLS-Nystrom
Official TensorFlow implementation for AIHC, Springer 2021 paper: "A Two-tier Feature Selection Method using Coalition Game and Nystrom Sampling for Screening COVID-19 from Chest X-Ray Images".
Spring 2017 Large Scale Matrix Computation and Machine Learning project investigating spectral clustering on big data
Topology-aware cut-cell utilities for trimmed-domain kernel integration.
A Python implementation of the Diffusion Maps algorithm for non-linear dimensionality reduction, designed to follow scikit-learn conventions.
Monte-Carlo Nystrom method in NumPy / PyTorch
Repository containing the files for Project 2, course "HPC for numerical methods and data analysis", Fall 2024, EPFL
Robert Nystrom's Game Programming Patterns, implemented in C++ on top of Storm Engine v2 with igloo specs.
Script, demo e codice ausiliario per "Soluzione numerica di equazioni integrali di Fredholm su domini poligonali"
Spectral theory says ViT attention is low-rank. In practice, pure low-rank breaks the model — a reproducible benchmark of 7 attention approximations for Vision Transformers.
An experimental transpiler to C from the Lox programming language written in C# (Robert Nystrom: Crafting Interpreters)
To associate your repository with the nystrom topic, visit your repo's landing page and select "manage topics."