mlx-vis: GPU-Native Dimensionality Reduction on Apple Silicon
Authors
Han Xiao (Jina AI by Elastic)
Presentation
- Session
- Lost in Dimensions
- Time
- Thursday, Nov 12, 15:45 – 15:54 (US/Eastern) · session 15:00 – 16:30
- Location
- Hall Essex north
Links
Sign in to access the preprint PDF.
Sign in- Download Supplemental Material
Keywords
Dimensionality reduction, Apple Silicon, MLX, Metal GPU, hardware-aware computation, scientific visualization.
Abstract
Dimensionality reduction is a foundational tool for visualizing high-dimensional data, yet its reference implementations span a fragmented stack of CPU-bound Python packages that leaves the Metal GPU on Apple Silicon entirely unused. We present mlx-vis, a library that reimplements seven widely used dimensionality reduction methods and k-nearest neighbor graph construction in pure MLX, with every stage---from PCA preprocessing through embedding optimization to a circle-splatting renderer---executing on GPU. On Fashion-MNIST 70K, all seven methods embed in 2.1--4.6 s on an M3 Ultra, achieving 3--13x speedups over CPU baselines while reducing the entire dependency stack to MLX and NumPy. The same pipeline scales to ten million points on a single workstation. Code at https://github.com/hanxiao/mlx-vis.
For Practitioners
Data scientists, ML engineers, and visualization researchers who work on Apple Silicon hardware and need fast, low-dependency dimensionality reduction and 2D embedding visualization without a CUDA GPU. They can drop mlx-vis into exploratory data analysis pipelines to embed and render large datasets locally on a Mac, avoiding cloud GPUs and heavy CPU-bound toolchains.