# Deep Learning Multidimensional Projections

## TL;DR

This paper introduces a deep learning approach to generate fast, stable, and out-of-sample capable multidimensional projections, improving upon traditional methods like t-SNE in efficiency and usability.

## Contribution

It presents a novel neural network-based method to learn and replicate multidimensional projections, significantly enhancing speed, stability, and out-of-sample handling over existing techniques.

## Key findings

- Achieves 2-3 orders of magnitude faster projections than SNE-class methods.
- Handles out-of-sample data with stability and no complex parameters.
- Successfully applied to real-world high-dimensional datasets.

## Abstract

Dimensionality reduction methods, also known as projections, are frequently used for exploring multidimensional data in machine learning, data science, and information visualization. Among these, t-SNE and its variants have become very popular for their ability to visually separate distinct data clusters. However, such methods are computationally expensive for large datasets, suffer from stability problems, and cannot directly handle out-of-sample data. We propose a learning approach to construct such projections. We train a deep neural network based on a collection of samples from a given data universe, and their corresponding projections, and next use the network to infer projections of data from the same, or similar, universes. Our approach generates projections with similar characteristics as the learned ones, is computationally two to three orders of magnitude faster than SNE-class methods, has no complex-to-set user parameters, handles out-of-sample data in a stable manner, and can be used to learn any projection technique. We demonstrate our proposal on several real-world high dimensional datasets from machine learning.