A Flexible and Powerful Parameter Server for large-scale machine learning

A high-performance distributed deep learning system targeting large-scale and automated distributed training.

Implements "Clustering a Million Faces by Identity"

Octree/Quadtree/N-dimensional linear tree

Open and explore HDF5 files in JupyterLab. Can handle very large (TB) sized files, and datasets of any dimensionality

A fast, accurate, and modularized dimensionality reduction approach based on diffusion harmonics and graph layouts. Escalates to millions of samples on a personal laptop. Adds high-dimensional big data intrinsic structure to your clustering and data visualization workflow.

Simple and efficient Python package for modeling d-dimensional Bravais lattices in solid state physics.

A numerical library for High-Dimensional option Pricing problems, including Fourier transform methods, Monte Carlo methods and the Deep Galerkin method

Particle Swarm Optimization Visualization

Numerical illustration of a novel analysis framework for consensus-based optimization (CBO) and numerical experiments demonstrating the practicability of the method

DataHigh: A graphical user interface for visualizing and interacting with high-dimensional neural activity

[TMLR' 24] High-dimensional Bayesian Optimization via Covariance Matrix Adaptation Strategy

BioMM: Biological-informed Multi-stage Machine learning framework for phenotype prediction using omics data

Controlled Invariant Sets in Two Moves

Regularization Paths for Huber Loss Regression and Quantile Regression Penalized by Lasso or Elastic-Net

SpokeDarts sphere-packing sampling in any dimension. Advancing front sampling from radial lines (spokes) through prior samples.

flameplot is a python package for the quantification of local similarity across two maps or embeddings.

Video Input Generative Adversarial Imitation Learning

Implementation of the FNETS methodology proposed in Barigozzi, Cho and Owens (2024) for network estimation and forecasting of high-dimensional time series

DynSyn: Dynamical Synergistic Representation for Efficient Learning and Control in Overactuated Embodied Systems